Yao Wan

Yue Huang, Jiawen Shi, Yuan Li et al.

Large language models (LLMs) have garnered significant attention due to their impressive natural language processing (NLP) capabilities. Recently, many studies have focused on the tool utilization ability of LLMs. They primarily investigated how LLMs effectively collaborate with given specific tools. However, in scenarios where LLMs serve as intelligent agents, as seen in applications like AutoGPT and MetaGPT, LLMs are expected to engage in intricate decision-making processes that involve deciding whether to employ a tool and selecting the most suitable tool(s) from a collection of available tools to fulfill user requests. Therefore, in this paper, we introduce MetaTool, a benchmark designed to evaluate whether LLMs have tool usage awareness and can correctly choose tools. Specifically, we create a dataset called ToolE within the benchmark. This dataset contains various types of user queries in the form of prompts that trigger LLMs to use tools, including both single-tool and multi-tool scenarios. Subsequently, we set the tasks for both tool usage awareness and tool selection. We define four subtasks from different perspectives in tool selection, including tool selection with similar choices, tool selection in specific scenarios, tool selection with possible reliability issues, and multi-tool selection. We conduct experiments involving eight popular LLMs and find that the majority of them still struggle to effectively select tools, highlighting the existing gaps between LLMs and genuine intelligent agents. However, through the error analysis, we found there is still significant room for improvement. Finally, we conclude with insights for tool developers -- we strongly recommend that tool developers choose an appropriate rewrite model for generating new descriptions based on the downstream LLM the tool will apply to. Our code is in https://github.com/HowieHwong/MetaTool.

Wenting Zhao, Ye Liu, Yao Wan et al. · salesforce

Question answering on tabular data (a.k.a TableQA), which aims at generating answers to questions grounded on a provided table, has gained significant attention recently. Prior work primarily produces concise factual responses through information extraction from individual or limited table cells, lacking the ability to reason across diverse table cells. Yet, the realm of free-form TableQA, which demands intricate strategies for selecting relevant table cells and the sophisticated integration and inference of discrete data fragments, remains mostly unexplored. To this end, this paper proposes a generalized three-stage approach: Table-to- Graph conversion and cell localizing, external knowledge retrieval, and the fusion of table and text (called TAG-QA), to address the challenge of inferring long free-form answers in generative TableQA. In particular, TAG-QA (1) locates relevant table cells using a graph neural network to gather intersecting cells between relevant rows and columns, (2) leverages external knowledge from Wikipedia, and (3) generates answers by integrating both tabular data and natural linguistic information. Experiments showcase the superior capabilities of TAG-QA in generating sentences that are both faithful and coherent, particularly when compared to several state-of-the-art baselines. Notably, TAG-QA surpasses the robust pipeline-based baseline TAPAS by 17% and 14% in terms of BLEU-4 and PARENT F-score, respectively. Furthermore, TAG-QA outperforms the end-to-end model T5 by 16% and 12% on BLEU-4 and PARENT F-score, respectively.

Wenting Zhao, Ye Liu, Tong Niu et al.

Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when solely relying on their internal knowledge, especially when answering questions that require less commonly known information. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge. Nonetheless, recent approaches have primarily emphasized retrieval from unstructured text corpora, owing to its seamless integration into prompts. When using structured data such as knowledge graphs, most methods simplify it into natural text, neglecting the underlying structures. Moreover, a significant gap in the current landscape is the absence of a realistic benchmark for evaluating the effectiveness of grounding LLMs on heterogeneous knowledge sources (e.g., knowledge base and text). To fill this gap, we have curated a comprehensive dataset that poses two unique challenges: (1) Two-hop multi-source questions that require retrieving information from both open-domain structured and unstructured knowledge sources; retrieving information from structured knowledge sources is a critical component in correctly answering the questions. (2) The generation of symbolic queries (e.g., SPARQL for Wikidata) is a key requirement, which adds another layer of challenge. Our dataset is created using a combination of automatic generation through predefined reasoning chains and human annotation. We also introduce a novel approach that leverages multiple retrieval tools, including text passage retrieval and symbolic language-assisted retrieval. Our model outperforms previous approaches by a significant margin, demonstrating its effectiveness in addressing the above-mentioned reasoning challenges.

Dongping Chen, Jiawen Shi, Yao Wan et al.

While Large Language Models (LLMs) have achieved remarkable success across various applications, they also raise concerns regarding self-cognition. In this paper, we perform a pioneering study to explore self-cognition in LLMs. Specifically, we first construct a pool of self-cognition instruction prompts to evaluate where an LLM exhibits self-cognition and four well-designed principles to quantify LLMs' self-cognition. Our study reveals that 4 of the 48 models on Chatbot Arena--specifically Command R, Claude3-Opus, Llama-3-70b-Instruct, and Reka-core--demonstrate some level of detectable self-cognition. We observe a positive correlation between model size, training data quality, and self-cognition level. Additionally, we also explore the utility and trustworthiness of LLM in the self-cognition state, revealing that the self-cognition state enhances some specific tasks such as creative writing and exaggeration. We believe that our work can serve as an inspiration for further research to study the self-cognition in LLMs.

Qihui Zhang, Chujie Gao, Dongping Chen et al.

With the rapid development and widespread application of Large Language Models (LLMs), the use of Machine-Generated Text (MGT) has become increasingly common, bringing with it potential risks, especially in terms of quality and integrity in fields like news, education, and science. Current research mainly focuses on purely MGT detection without adequately addressing mixed scenarios, including AI-revised Human-Written Text (HWT) or human-revised MGT. To tackle this challenge, we define mixtext, a form of mixed text involving both AI and human-generated content. Then, we introduce MixSet, the first dataset dedicated to studying these mixtext scenarios. Leveraging MixSet, we executed comprehensive experiments to assess the efficacy of prevalent MGT detectors in handling mixtext situations, evaluating their performance in terms of effectiveness, robustness, and generalization. Our findings reveal that existing detectors struggle to identify mixtext, particularly in dealing with subtle modifications and style adaptability. This research underscores the urgent need for more fine-grain detectors tailored for mixtext, offering valuable insights for future research. Code and Models are available at https://github.com/Dongping-Chen/MixSet.

Yao Wan, Yang He, Zhangqian Bi et al.

Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality and productivity of computer programming. Currently, there is already a thriving research community focusing on code intelligence, with efforts ranging from software engineering, machine learning, data mining, natural language processing, and programming languages. In this paper, we conduct a comprehensive literature review on deep learning for code intelligence, from the aspects of code representation learning, deep learning techniques, and application tasks. We also benchmark several state-of-the-art neural models for code intelligence, and provide an open-source toolkit tailored for the rapid prototyping of deep-learning-based code intelligence models. In particular, we inspect the existing code intelligence models under the basis of code representation learning, and provide a comprehensive overview to enhance comprehension of the present state of code intelligence. Furthermore, we publicly release the source code and data resources to provide the community with a ready-to-use benchmark, which can facilitate the evaluation and comparison of existing and future code intelligence models (https://xcodemind.github.io). At last, we also point out several challenging and promising directions for future research.

Zetong Zhou, Dongping Chen, Zixian Ma et al.

Visual reasoning, a cornerstone of human intelligence, encompasses complex perceptual and logical processes essential for solving diverse visual problems. While advances in computer vision have produced powerful models for various perceptual tasks, leveraging these for general visual reasoning remains challenging. Prior work demonstrates that augmenting LLMs with vision models via supervised finetuning improves performance, but faces key limitations such as expensive data generation, reliance on careful data filtering, and poor generalization. To address these issues, we propose ReVPT to enhance multi-modal LLMs' abilities to reason about and use visual tools through reinforcement learning. We introduce a novel RL algorithm based on GRPO, designed to train models to reason with a suite of four visual tools. Through extensive experiments, we show that our method achieves state-of-the-art performance on several perception-heavy benchmarks, including SAT, CV-Bench, BLINK and MMStar, significantly outperforming the supervised and text-based RL finetuning baselines. Notably, Our ReVPT-3B and ReVPT-7B outperform the instruct models by 9.03% and 9.44% on CV-Bench. Finally, we bring to the community new insights on RL-based visual tool-usage through extensive ablations. Our code is available at https://github.com/ls-kelvin/REVPT.

Yisen Li, Lingfeng Yang, Wenxuan Shen et al.

Distilling advanced Large Language Models' instruction-following capabilities into smaller models using a selected subset has become a mainstream approach in model training. While existing synthetic instruction data selection strategies rely mainly on single-dimensional signals (i.e., reward scores, model perplexity), they fail to capture the complexity of instruction-following across diverse fields. Therefore, we investigate more diverse signals to capture comprehensive instruction-response pair characteristics and propose three foundational metrics that leverage Multi-LLM wisdom, informed by (1) diverse LLM responses and (2) reward model assessment. Building upon base metrics, we propose CrowdSelect, an integrated metric incorporating a clustering-based approach to maintain response diversity. Our comprehensive experiments demonstrate that our foundation metrics consistently improve performance across 4 base models on MT-bench and Arena-Hard. CrowdSelect, efficiently incorporating all metrics, achieves state-of-the-art performance in both Full and LoRA fine-tuning, showing improvements of 4.81% on Arena-Hard and 11.1% on MT-bench with Llama-3.2-3b-instruct. We hope our findings will bring valuable insights for future research in this direction. Code are available at https://github.com/listentm/crowdselect.

Dongping Chen, Ruoxi Chen, Shilin Zhang et al.

Multimodal Large Language Models (MLLMs) have gained significant attention recently, showing remarkable potential in artificial general intelligence. However, assessing the utility of MLLMs presents considerable challenges, primarily due to the absence of multimodal benchmarks that align with human preferences. Drawing inspiration from the concept of LLM-as-a-Judge within LLMs, this paper introduces a novel benchmark, termed MLLM-as-a-Judge, to assess the ability of MLLMs in assisting judges across diverse modalities, encompassing three distinct tasks: Scoring Evaluation, Pair Comparison, and Batch Ranking. Our study reveals that, while MLLMs demonstrate remarkable human-like discernment in Pair Comparison, there is a significant divergence from human preferences in Scoring Evaluation and Batch Ranking. Furthermore, a closer examination reveals persistent challenges in the judgment capacities of LLMs, including diverse biases, hallucinatory responses, and inconsistencies in judgment, even in advanced models such as GPT-4V. These findings emphasize the pressing need for enhancements and further research efforts to be undertaken before regarding MLLMs as fully reliable evaluators. In light of this, we advocate for additional efforts dedicated to supporting the continuous development within the domain of MLLM functioning as judges. The code and dataset are publicly available at our project homepage: \url{https://mllm-judge.github.io/}.

Zhangqian Bi, Yao Wan, Zhaoyang Chu et al.

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pretraining language models on a large-scale code corpus is computationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pretraining, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used opensource PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks.

Yao Wan, Jingdong Shu, Yulei Sui et al.

Code retrieval techniques and tools have been playing a key role in facilitating software developers to retrieve existing code fragments from available open-source repositories given a user query. Despite the existing efforts in improving the effectiveness of code retrieval, there are still two main issues hindering them from being used to accurately retrieve satisfiable code fragments from large-scale repositories when answering complicated queries. First, the existing approaches only consider shallow features of source code such as method names and code tokens, but ignoring structured features such as abstract syntax trees (ASTs) and control-flow graphs (CFGs) of source code, which contains rich and well-defined semantics of source code. Second, although the deep learning-based approach performs well on the representation of source code, it lacks the explainability, making it hard to interpret the retrieval results and almost impossible to understand which features of source code contribute more to the final results. To tackle the two aforementioned issues, this paper proposes MMAN, a novel Multi-Modal Attention Network for semantic source code retrieval. A comprehensive multi-modal representation is developed for representing unstructured and structured features of source code, with one LSTM for the sequential tokens of code, a Tree-LSTM for the AST of code and a GGNN (Gated Graph Neural Network) for the CFG of code. Furthermore, a multi-modal attention fusion layer is applied to assign weights to different parts of each modality of source code and then integrate them into a single hybrid representation. Comprehensive experiments and analysis on a large-scale real-world dataset show that our proposed model can accurately retrieve code snippets and outperforms the state-of-the-art methods.

Yang Wu, Yao Wan, Hongyu Zhang et al.

The Natural Language to Visualization (NL2Vis) task aims to transform natural-language descriptions into visual representations for a grounded table, enabling users to gain insights from vast amounts of data. Recently, many deep learning-based approaches have been developed for NL2Vis. Despite the considerable efforts made by these approaches, challenges persist in visualizing data sourced from unseen databases or spanning multiple tables. Taking inspiration from the remarkable generation capabilities of Large Language Models (LLMs), this paper conducts an empirical study to evaluate their potential in generating visualizations, and explore the effectiveness of in-context learning prompts for enhancing this task. In particular, we first explore the ways of transforming structured tabular data into sequential text prompts, as to feed them into LLMs and analyze which table content contributes most to the NL2Vis. Our findings suggest that transforming structured tabular data into programs is effective, and it is essential to consider the table schema when formulating prompts. Furthermore, we evaluate two types of LLMs: finetuned models (e.g., T5-Small) and inference-only models (e.g., GPT-3.5), against state-of-the-art methods, using the NL2Vis benchmarks (i.e., nvBench). The experimental results reveal that LLMs outperform baselines, with inference-only models consistently exhibiting performance improvements, at times even surpassing fine-tuned models when provided with certain few-shot demonstrations through in-context learning. Finally, we analyze when the LLMs fail in NL2Vis, and propose to iteratively update the results using strategies such as chain-of-thought, role-playing, and code-interpreter. The experimental results confirm the efficacy of iterative updates and hold great potential for future study.

Zhangqian Bi, Yao Wan, Zheng Wang et al.

Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-generated code may contain errors in API usage, class, data structure, or missing project-specific information. As much of this project-specific context cannot fit into the prompts of LLMs, we must find ways to allow the model to explore the project-level code context. We present CoCoGen, a new code generation approach that uses compiler feedback to improve the LLM-generated code. CoCoGen first leverages static analysis to identify mismatches between the generated code and the project's context. It then iteratively aligns and fixes the identified errors using information extracted from the code repository. We integrate CoCoGen with two representative LLMs, i.e., GPT-3.5-Turbo and Code Llama (13B), and apply it to Python code generation. Experimental results show that CoCoGen significantly improves the vanilla LLMs by over 80% in generating code dependent on the project context and consistently outperforms the existing retrieval-based code generation baselines.

Zhaoyang Chu, Yao Wan, Qian Li et al.

Vulnerability detection is crucial for ensuring the security and reliability of software systems. Recently, Graph Neural Networks (GNNs) have emerged as a prominent code embedding approach for vulnerability detection, owing to their ability to capture the underlying semantic structure of source code. However, GNNs face significant challenges in explainability due to their inherently black-box nature. To this end, several factual reasoning-based explainers have been proposed. These explainers provide explanations for the predictions made by GNNs by analyzing the key features that contribute to the outcomes. We argue that these factual reasoning-based explanations cannot answer critical what-if questions: What would happen to the GNN's decision if we were to alter the code graph into alternative structures? Inspired by advancements of counterfactual reasoning in artificial intelligence, we propose CFExplainer, a novel counterfactual explainer for GNN-based vulnerability detection. Unlike factual reasoning-based explainers, CFExplainer seeks the minimal perturbation to the input code graph that leads to a change in the prediction, thereby addressing the what-if questions for vulnerability detection. We term this perturbation a counterfactual explanation, which can pinpoint the root causes of the detected vulnerability and furnish valuable insights for developers to undertake appropriate actions for fixing the vulnerability. Extensive experiments on four GNN-based vulnerability detection models demonstrate the effectiveness of CFExplainer over existing state-of-the-art factual reasoning-based explainers.

Yi Gui, Zhen Li, Yao Wan et al.

Automatically generating webpage code from webpage designs can significantly reduce the workload of front-end developers, and recent Multimodal Large Language Models (MLLMs) have shown promising potential in this area. However, our investigation reveals that most existing MLLMs are constrained by the absence of high-quality, large-scale, real-world datasets, resulting in inadequate performance in automated webpage code generation. To fill this gap, this paper introduces WebCode2M, a new dataset comprising 2.56 million instances, each containing a design image along with the corresponding webpage code and layout details. Sourced from real-world web resources, WebCode2M offers a rich and valuable dataset for webpage code generation across a variety of applications. The dataset quality is ensured by a scoring model that filters out instances with aesthetic deficiencies or other incomplete elements. To validate the effectiveness of WebCode2M, we introduce a baseline model based on the Vision Transformer (ViT), named WebCoder, and establish a benchmark for fair comparison. Additionally, we introduce a new metric, TreeBLEU, to measure the structural hierarchy recall. The benchmarking results demonstrate that our dataset significantly improves the ability of MLLMs to generate code from webpage designs, confirming its effectiveness and usability for future applications in front-end design tools. Finally, we highlight several practical challenges introduced by our dataset, calling for further research. The code and dataset are publicly available at our project homepage: https://webcode2m.github.io.

Batu Guan, Yao Wan, Zhangqian Bi et al.

Large Language Models (LLMs) have achieved remarkable progress in code generation. It now becomes crucial to identify whether the code is AI-generated and to determine the specific model used, particularly for purposes such as protecting Intellectual Property (IP) in industry and preventing cheating in programming exercises. To this end, several attempts have been made to insert watermarks into machine-generated code. However, existing approaches are limited to inserting only a single bit of information. In this paper, we introduce CodeIP, a novel multi-bit watermarking technique that inserts additional information to preserve crucial provenance details, such as the vendor ID of an LLM, thereby safeguarding the IPs of LLMs in code generation. Furthermore, to ensure the syntactical correctness of the generated code, we propose constraining the sampling process for predicting the next token by training a type predictor. Experiments conducted on a real-world dataset across five programming languages demonstrate the effectiveness of CodeIP in watermarking LLMs for code generation while maintaining the syntactical correctness of code.

Geliang Ouyang, Jingyao Chen, Zhihe Nie et al.

Natural Language to Visualization (NL2Vis) seeks to convert natural-language descriptions into visual representations of given tables, empowering users to derive insights from large-scale data. Recent advancements in Large Language Models (LLMs) show promise in automating code generation to transform tabular data into accessible visualizations. However, they often struggle with complex queries that require reasoning across multiple tables. To address this limitation, we propose a collaborative agent workflow, termed nvAgent, for NL2Vis. Specifically, nvAgent comprises three agents: a processor agent for database processing and context filtering, a composer agent for planning visualization generation, and a validator agent for code translation and output verification. Comprehensive evaluations on the new VisEval benchmark demonstrate that nvAgent consistently surpasses state-of-the-art baselines, achieving a 7.88% improvement in single-table and a 9.23% improvement in multi-table scenarios. Qualitative analyses further highlight that nvAgent maintains nearly a 20% performance margin over previous models, underscoring its capacity to produce high-quality visual representations from complex, heterogeneous data sources.

Dongping Chen, Ruoxi Chen, Shu Pu et al.

Many real-world user queries (e.g. "How do to make egg fried rice?") could benefit from systems capable of generating responses with both textual steps with accompanying images, similar to a cookbook. Models designed to generate interleaved text and images face challenges in ensuring consistency within and across these modalities. To address these challenges, we present ISG, a comprehensive evaluation framework for interleaved text-and-image generation. ISG leverages a scene graph structure to capture relationships between text and image blocks, evaluating responses on four levels of granularity: holistic, structural, block-level, and image-specific. This multi-tiered evaluation allows for a nuanced assessment of consistency, coherence, and accuracy, and provides interpretable question-answer feedback. In conjunction with ISG, we introduce a benchmark, ISG-Bench, encompassing 1,150 samples across 8 categories and 21 subcategories. This benchmark dataset includes complex language-vision dependencies and golden answers to evaluate models effectively on vision-centric tasks such as style transfer, a challenging area for current models. Using ISG-Bench, we demonstrate that recent unified vision-language models perform poorly on generating interleaved content. While compositional approaches that combine separate language and image models show a 111% improvement over unified models at the holistic level, their performance remains suboptimal at both block and image levels. To facilitate future work, we develop ISG-Agent, a baseline agent employing a "plan-execute-refine" pipeline to invoke tools, achieving a 122% performance improvement.

Wenting Zhao, Ye Liu, Yao Wan et al.

Task-Oriented Parsing (TOP) enables conversational assistants to interpret user commands expressed in natural language, transforming them into structured outputs that combine elements of both natural language and intent/slot tags. Recently, Large Language Models (LLMs) have achieved impressive performance in synthesizing computer programs based on a natural language prompt, mitigating the gap between natural language and structured programs. Our paper focuses on harnessing the capabilities of LLMs for semantic parsing tasks, addressing the following three key research questions: 1) How can LLMs be effectively utilized for semantic parsing tasks? 2) What defines an effective prompt? and 3) How can LLM overcome the length constraint and streamline prompt design by including all examples as prompts? We introduce k Nearest Neighbor In-Context Learning(kNN-ICL), which simplifies prompt engineering by allowing it to be built on top of any design strategy while providing access to all demo examples. Extensive experiments show that: 1)Simple ICL without kNN search can achieve a comparable performance with strong supervised models on the TOP tasks, and 2) kNN-ICL significantly improves the comprehension of complex requests by seamlessly integrating ICL with a nearest-neighbor approach. Notably, this enhancement is achieved without the need for additional data or specialized prompts.

Yao Wan, Guanghua Wan, Shijie Zhang et al.

Recent years have witnessed significant progress in developing deep learning-based models for automated code completion. Although using source code in GitHub has been a common practice for training deep-learning-based models for code completion, it may induce some legal and ethical issues such as copyright infringement. In this paper, we investigate the legal and ethical issues of current neural code completion models by answering the following question: Is my code used to train your neural code completion model? To this end, we tailor a membership inference approach (termed CodeMI) that was originally crafted for classification tasks to a more challenging task of code completion. In particular, since the target code completion models perform as opaque black boxes, preventing access to their training data and parameters, we opt to train multiple shadow models to mimic their behavior. The acquired posteriors from these shadow models are subsequently employed to train a membership classifier. Subsequently, the membership classifier can be effectively employed to deduce the membership status of a given code sample based on the output of a target code completion model. We comprehensively evaluate the effectiveness of this adapted approach across a diverse array of neural code completion models, (i.e., LSTM-based, CodeGPT, CodeGen, and StarCoder). Experimental results reveal that the LSTM-based and CodeGPT models suffer the membership leakage issue, which can be easily detected by our proposed membership inference approach with an accuracy of 0.842, and 0.730, respectively. Interestingly, our experiments also show that the data membership of current large language models of code, e.g., CodeGen and StarCoder, is difficult to detect, leaving ampler space for further improvement. Finally, we also try to explain the findings from the perspective of model memorization.

Wei Zhao, Zhitao Hou, Siyuan Wu et al.

Writing formulas on spreadsheets, such as Microsoft Excel and Google Sheets, is a widespread practice among users performing data analysis. However, crafting formulas on spreadsheets remains a tedious and error-prone task for many end-users, particularly when dealing with complex operations. To alleviate the burden associated with writing spreadsheet formulas, this paper introduces a novel benchmark task called NL2Formula, with the aim to generate executable formulas that are grounded on a spreadsheet table, given a Natural Language (NL) query as input. To accomplish this, we construct a comprehensive dataset consisting of 70,799 paired NL queries and corresponding spreadsheet formulas, covering 21,670 tables and 37 types of formula functions. We realize the NL2Formula task by providing a sequence-to-sequence baseline implementation called fCoder. Experimental results validate the effectiveness of fCoder, demonstrating its superior performance compared to the baseline models. Furthermore, we also compare fCoder with an initial GPT-3.5 model (i.e., text-davinci-003). Lastly, through in-depth error analysis, we identify potential challenges in the NL2Formula task and advocate for further investigation.

Siming Huang, Yuliang Xu, Mingmeng Geng et al.

In this paper, we present a thorough analysis of the impact of Large Language Models (LLMs) on Wikipedia, examining the evolution of Wikipedia through existing data and using simulations to explore potential risks. We begin by analyzing page views and article content to study Wikipedia's recent changes and assess the impact of LLMs. Subsequently, we evaluate how LLMs affect various Natural Language Processing (NLP) tasks related to Wikipedia, including machine translation and retrieval-augmented generation (RAG). Our findings and simulation results reveal that Wikipedia articles have been influenced by LLMs, with an impact of approximately 1%-2% in certain categories. If the machine translation benchmark based on Wikipedia is influenced by LLMs, the scores of the models may become inflated, and the comparative results among models might shift as well. Moreover, the effectiveness of RAG might decrease if the knowledge base becomes polluted by LLM-generated content. While LLMs have not yet fully changed Wikipedia's language and knowledge structures, we believe that our empirical findings signal the need for careful consideration of potential future risks.

Mingyang Fu, Yuyang Peng, Dongping Chen et al.

The visual world around us constantly evolves, from real-time news and social media trends to global infrastructure changes visible through satellite imagery and augmented reality enhancements. However, Multimodal Large Language Models (MLLMs), which automate many tasks, struggle to stay current, limited by the cutoff dates in their fixed training datasets. To quantify this stagnation, we introduce LiveVQA, the first-of-its-kind dataset featuring 107,143 samples and 12 categories data specifically designed to support research in both seeking and updating with live visual knowledge. Drawing from recent news articles, video platforms, and academic publications in April 2024-May 2025, LiveVQA enables evaluation of how models handle latest visual information beyond their knowledge boundaries and how current methods help to update them. Our comprehensive benchmarking of 17 state-of-the-art MLLMs reveals significant performance gaps on content beyond knowledge cutoff, and tool-use or agentic visual seeking framework drastically gain an average of 327% improvement. Furthermore, we explore parameter-efficient fine-tuning (PEFT) methods to update MLLMs with new visual knowledge. We dive deeply to the critical balance between adapter capacity and model capability when updating MLLMs with new visual knowledge. All the experimental dataset and source code are publicly available at: https://livevqa.github.io.

Ruoxi Chen, Dongping Chen, Siyuan Wu et al. · allen-ai, uw

Visual designers naturally draw inspiration from multiple visual references, combining diverse elements and aesthetic principles to create artwork. However, current image generative frameworks predominantly rely on single-source inputs -- either text prompts or individual reference images. In this paper, we focus on the task of controllable image generation using multiple visual references. We introduce MultiRef-bench, a rigorous evaluation framework comprising 990 synthetic and 1,000 real-world samples that require incorporating visual content from multiple reference images. The synthetic samples are synthetically generated through our data engine RefBlend, with 10 reference types and 33 reference combinations. Based on RefBlend, we further construct a dataset MultiRef containing 38k high-quality images to facilitate further research. Our experiments across three interleaved image-text models (i.e., OmniGen, ACE, and Show-o) and six agentic frameworks (e.g., ChatDiT and LLM + SD) reveal that even state-of-the-art systems struggle with multi-reference conditioning, with the best model OmniGen achieving only 66.6% in synthetic samples and 79.0% in real-world cases on average compared to the golden answer. These findings provide valuable directions for developing more flexible and human-like creative tools that can effectively integrate multiple sources of visual inspiration. The dataset is publicly available at: https://multiref.github.io/.

Zhaoyang Chu, Yao Wan, Zhikun Zhang et al.

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit unintended memorization of sensitive training data, enabling verbatim reproduction of confidential information when specifically prompted. To address this issue, several approaches, including training data de-duplication and differential privacy augmentation, have been proposed. However, these methods require full-model retraining for deployed CLMs, which incurs substantial computational costs. In this paper, we aim to answer the following research question: Can sensitive information memorized by CLMs be erased effectively and efficiently? We conduct a pioneering investigation into erasing sensitive memorization in CLMs through machine unlearning - a post-hoc modification method that removes specific information from trained models without requiring full retraining. Specifically, we first quantify the memorization risks of sensitive data within CLM training datasets and curate a high-risk dataset of 50,000 sensitive memorized samples as unlearning targets. We study two widely used gradient ascent-based unlearning approaches: the vanilla and constraint-based methods, and introduce CodeEraser, an advanced variant that selectively unlearns sensitive memorized segments in code while preserving the structural integrity and functional correctness of the surrounding code. Extensive experiments on three families of CLMs, i.e., CodeParrot, CodeGen-Mono, and Qwen2.5-Coder, validate the effectiveness and efficiency of CodeEraser in erasing targeted sensitive memorization while maintaining model utility.

Hailong Jiang, Jianfeng Zhu, Yao Wan et al.

Intermediate Representations (IRs) play a critical role in compiler design and program analysis, yet their comprehension by Large Language Models (LLMs) remains underexplored. In this paper, we present an explorative empirical study evaluating the capabilities of six state-of-the-art LLMs: GPT-4, GPT-3, DeepSeek, Gemma 2, Llama 3, and Code Llama, in understanding IRs. Specifically, we assess model performance across four core tasks: control flow graph reconstruction, decompilation, code summarization, and execution reasoning. While LLMs exhibit competence in parsing IR syntax and identifying high-level structures, they consistently struggle with instruction-level reasoning, especially in control flow reasoning, loop handling, and dynamic execution. Common failure modes include misinterpreting branching instructions, omitting critical operations, and relying on heuristic reasoning rather than precise instruction-level logic. Our findings highlight the need for IR-specific enhancements in LLM design. We recommend fine-tuning on structured IR datasets and integrating control-flow-sensitive architectures to improve model effectiveness. All experimental data and source code are publicly available at

Junxiao Han, Yarong Wang, Xiaodong Gu et al.

In this paper, we propose LibRec, a novel framework that integrates the capabilities of LLMs with retrieval-augmented generation(RAG) techniques to automate the recommendation of alternative libraries. The framework further employs in-context learning to extract migration intents from commit messages to enhance the accuracy of its recommendations. To evaluate the effectiveness of LibRec, we introduce LibEval, a benchmark designed to assess the performance in the library migration recommendation task. LibEval comprises 2,888 migration records associated with 2,368 libraries extracted from 2,324 Python repositories. Each migration record captures source-target library pairs, along with their corresponding migration intents and intent types. Based on LibEval, we evaluated the effectiveness of ten popular LLMs within our framework, conducted an ablation study to examine the contributions of key components within our framework, explored the impact of various prompt strategies on the framework's performance, assessed its effectiveness across various intent types, and performed detailed failure case analyses.

Yuliang Xu, Siming Huang, Mingmeng Geng et al.

Coding remains one of the most fundamental modes of interaction between humans and machines. With the rapid advancement of Large Language Models (LLMs), code generation capabilities have begun to significantly reshape programming practices. This development prompts a central question: Have LLMs transformed code style, and how can such transformation be characterized? In this paper, we present a pioneering study that investigates the impact of LLMs on code style, with a focus on naming conventions, complexity, maintainability, and similarity. By analyzing code from over 19,000 GitHub repositories linked to arXiv papers published between 2020 and 2025, we identify measurable trends in the evolution of coding style that align with characteristics of LLM-generated code. For instance, the proportion of snake\_case variable names in Python code increased from 47% in Q1 2023 to 51% in Q1 2025. Furthermore, we investigate how LLMs approach algorithmic problems by examining their reasoning processes. Given the diversity of LLMs and usage scenarios, among other factors, it is difficult or even impossible to precisely estimate the proportion of code generated or assisted by LLMs. Our experimental results provide the first large-scale empirical evidence that LLMs affect real-world programming style.

Yue Huang, Siyuan Wu, Chujie Gao et al.

Large Language Models (LLMs) such as GPT-4 and Llama3 have significantly impacted various fields by enabling high-quality synthetic data generation and reducing dependence on expensive human-generated datasets. Despite this, challenges remain in the areas of generalization, controllability, diversity, and truthfulness within the existing generative frameworks. To address these challenges, this paper presents DataGen, a comprehensive LLM-powered framework designed to produce diverse, accurate, and highly controllable datasets. DataGen is adaptable, supporting all types of text datasets and enhancing the generative process through innovative mechanisms. To augment data diversity, DataGen incorporates an attribute-guided generation module and a group checking feature. For accuracy, it employs a code-based mathematical assessment for label verification alongside a retrieval-augmented generation technique for factual validation. The framework also allows for user-specified constraints, enabling customization of the data generation process to suit particular requirements. Extensive experiments demonstrate the superior quality of data generated by DataGen, and each module within DataGen plays a critical role in this enhancement. Additionally, DataGen is applied in two practical scenarios: benchmarking LLMs and data augmentation. The results indicate that DataGen effectively supports dynamic and evolving benchmarking and that data augmentation improves LLM capabilities in various domains, including agent-oriented abilities and reasoning skills.

Ye Liu, Jian-Guo Zhang, Yao Wan et al.

To capture the semantic graph structure from raw text, most existing summarization approaches are built on GNNs with a pre-trained model. However, these methods suffer from cumbersome procedures and inefficient computations for long-text documents. To mitigate these issues, this paper proposes HETFORMER, a Transformer-based pre-trained model with multi-granularity sparse attentions for long-text extractive summarization. Specifically, we model different types of semantic nodes in raw text as a potential heterogeneous graph and directly learn heterogeneous relationships (edges) among nodes by Transformer. Extensive experiments on both single- and multi-document summarization tasks show that HETFORMER achieves state-of-the-art performance in Rouge F1 while using less memory and fewer parameters.

Xin Wang, Yasheng Wang, Fei Mi et al.

Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence. Recently, many pre-trained language models for source code (e.g., CuBERT and CodeBERT) have been proposed to model the context of code and serve as a basis for downstream code intelligence tasks such as code search, code clone detection, and program translation. Current approaches typically consider the source code as a plain sequence of tokens, or inject the structure information (e.g., AST and data-flow) into the sequential model pre-training. To further explore the properties of programming languages, this paper proposes SynCoBERT, a syntax-guided multi-modal contrastive pre-training approach for better code representations. Specially, we design two novel pre-training objectives originating from the symbolic and syntactic properties of source code, i.e., Identifier Prediction (IP) and AST Edge Prediction (TEP), which are designed to predict identifiers, and edges between two nodes of AST, respectively. Meanwhile, to exploit the complementary information in semantically equivalent modalities (i.e., code, comment, AST) of the code, we propose a multi-modal contrastive learning strategy to maximize the mutual information among different modalities. Extensive experiments on four downstream tasks related to code intelligence show that SynCoBERT advances the state-of-the-art with the same pre-training corpus and model size.

Dezhong Yao, Wanning Pan, Yutong Dai et al.

Federated learning enables multiple clients to collaboratively learn a global model by periodically aggregating the clients' models without transferring the local data. However, due to the heterogeneity of the system and data, many approaches suffer from the "client-drift" issue that could significantly slow down the convergence of the global model training. As clients perform local updates on heterogeneous data through heterogeneous systems, their local models drift apart. To tackle this issue, one intuitive idea is to guide the local model training by the global teachers, i.e., past global models, where each client learns the global knowledge from past global models via adaptive knowledge distillation techniques. Coming from these insights, we propose a novel approach for heterogeneous federated learning, namely FedGKD, which fuses the knowledge from historical global models for local training to alleviate the "client-drift" issue. In this paper, we evaluate FedGKD with extensive experiments on various CV/NLP datasets (i.e., CIFAR-10/100, Tiny-ImageNet, AG News, SST5) and different heterogeneous settings. The proposed method is guaranteed to converge under common assumptions, and achieves superior empirical accuracy in fewer communication runs than five state-of-the-art methods.

Ye Liu, Yao Wan, Jian-Guo Zhang et al.

The non-autoregressive models have boosted the efficiency of neural machine translation through parallelized decoding at the cost of effectiveness when comparing with the autoregressive counterparts. In this paper, we claim that the syntactic and semantic structures among natural language are critical for non-autoregressive machine translation and can further improve the performance. However, these structures are rarely considered in the existing non-autoregressive models. Inspired by this intuition, we propose to incorporate the explicit syntactic and semantic structures of languages into a non-autoregressive Transformer, for the task of neural machine translation. Moreover, we also consider the intermediate latent alignment within target sentences to better learn the long-term token dependencies. Experimental results on two real-world datasets (i.e., WMT14 En-De and WMT16 En-Ro) show that our model achieves a significantly faster speed, as well as keeps the translation quality when compared with several state-of-the-art non-autoregressive models.

Yao Wan, Yang He, Jian-Guo Zhang et al.

We present NaturalCC, an efficient and extensible toolkit to bridge the gap between natural language and programming language, and facilitate the research on big code analysis. Using NaturalCC, researchers both from natural language or programming language communities can quickly and easily reproduce the state-of-the-art baselines and implement their approach. NaturalCC is built upon Fairseq and PyTorch, providing (1) an efficient computation with multi-GPU and mixed-precision data processing for fast model training, (2) a modular and extensible framework that makes it easy to reproduce or implement an approach for big code analysis, and (3) a command line interface and a graphical user interface to demonstrate each model's performance. Currently, we have included several state-of-the-art baselines across different tasks (e.g., code completion, code comment generation, and code retrieval) for demonstration. The video of this demo is available at https://www.youtube.com/watch?v=q4W5VSI-u3E&t=25s.

Jian-Guo Zhang, Kazuma Hashimoto, Wenhao Liu et al.

Intent detection is one of the core components of goal-oriented dialog systems, and detecting out-of-scope (OOS) intents is also a practically important skill. Few-shot learning is attracting much attention to mitigate data scarcity, but OOS detection becomes even more challenging. In this paper, we present a simple yet effective approach, discriminative nearest neighbor classification with deep self-attention. Unlike softmax classifiers, we leverage BERT-style pairwise encoding to train a binary classifier that estimates the best matched training example for a user input. We propose to boost the discriminative ability by transferring a natural language inference (NLI) model. Our extensive experiments on a large-scale multi-domain intent detection task show that our method achieves more stable and accurate in-domain and OOS detection accuracy than RoBERTa-based classifiers and embedding-based nearest neighbor approaches. More notably, the NLI transfer enables our 10-shot model to perform competitively with 50-shot or even full-shot classifiers, while we can keep the inference time constant by leveraging a faster embedding retrieval model.

Yue Wang, Zhuo Xu, Lu Bai et al.

Joint-event-extraction, which extracts structural information (i.e., entities or triggers of events) from unstructured real-world corpora, has attracted more and more research attention in natural language processing. Most existing works do not fully address the sparse co-occurrence relationships between entities and triggers, which loses this important information and thus deteriorates the extraction performance. To mitigate this issue, we first define the joint-event-extraction as a sequence-to-sequence labeling task with a tag set composed of tags of triggers and entities. Then, to incorporate the missing information in the aforementioned co-occurrence relationships, we propose a Cross-Supervised Mechanism (CSM) to alternately supervise the extraction of either triggers or entities based on the type distribution of each other. Moreover, since the connected entities and triggers naturally form a heterogeneous information network (HIN), we leverage the latent pattern along meta-paths for a given corpus to further improve the performance of our proposed method. To verify the effectiveness of our proposed method, we conduct extensive experiments on four real-world datasets as well as compare our method with state-of-the-art methods. Empirical results and analysis show that our approach outperforms the state-of-the-art methods in both entity and trigger extraction.

Ye Liu, Yao Wan, Lifang He et al.

Generative commonsense reasoning which aims to empower machines to generate sentences with the capacity of reasoning over a set of concepts is a critical bottleneck for text generation. Even the state-of-the-art pre-trained language generation models struggle at this task and often produce implausible and anomalous sentences. One reason is that they rarely consider incorporating the knowledge graph which can provide rich relational information among the commonsense concepts. To promote the ability of commonsense reasoning for text generation, we propose a novel knowledge graph augmented pre-trained language generation model KG-BART, which encompasses the complex relations of concepts through the knowledge graph and produces more logical and natural sentences as output. Moreover, KG-BART can leverage the graph attention to aggregate the rich concept semantics that enhances the model generalization on unseen concept sets. Experiments on benchmark CommonGen dataset verify the effectiveness of our proposed approach by comparing with several strong pre-trained language generation models, particularly KG-BART outperforms BART by 5.80, 4.60, in terms of BLEU-3, 4. Moreover, we also show that the generated context by our model can work as background scenarios to benefit downstream commonsense QA tasks.

Yue Wang, Yao Wan, Chenwei Zhang et al.

Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perform better in similar future tasks. This paper investigates the counterfactual thinking for agents to find optimal decision-making strategies in multi-agent reinforcement learning environments. In particular, we propose a multi-agent deep reinforcement learning model with a structure which mimics the human-psychological counterfactual thinking process to improve the competitive abilities for agents. To this end, our model generates several possible actions (intent actions) with a parallel policy structure and estimates the rewards and regrets for these intent actions based on its current understanding of the environment. Our model incorporates a scenario-based framework to link the estimated regrets with its inner policies. During the iterations, our model updates the parallel policies and the corresponding scenario-based regrets for agents simultaneously. To verify the effectiveness of our proposed model, we conduct extensive experiments on two different environments with real-world applications. Experimental results show that counterfactual thinking can actually benefit the agents to obtain more accumulative rewards from the environments with fair information by comparing to their opponents while keeping high performing efficiency.

Jian-Guo Zhang, Pengcheng Zou, Zhao Li et al.

Nowadays, more and more customers browse and purchase products in favor of using mobile E-Commerce Apps such as Taobao and Amazon. Since merchants are usually inclined to describe redundant and over-informative product titles to attract attentions from customers, it is important to concisely display short product titles on limited screen of mobile phones. To address this discrepancy, previous studies mainly consider textual information of long product titles and lacks of human-like view during training and evaluation process. In this paper, we propose a Multi-Modal Generative Adversarial Network (MM-GAN) for short product title generation in E-Commerce, which innovatively incorporates image information and attribute tags from product, as well as textual information from original long titles. MM-GAN poses short title generation as a reinforcement learning process, where the generated titles are evaluated by the discriminator in a human-like view. Extensive experiments on a large-scale E-Commerce dataset demonstrate that our algorithm outperforms other state-of-the-art methods. Moreover, we deploy our model into a real-world online E-Commerce environment and effectively boost the performance of click through rate and click conversion rate by 1.66% and 1.87%, respectively.

Yao Wan, Zhou Zhao, Min Yang et al.

Code summarization provides a high level natural language description of the function performed by code, as it can benefit the software maintenance, code categorization and retrieval. To the best of our knowledge, most state-of-the-art approaches follow an encoder-decoder framework which encodes the code into a hidden space and then decode it into natural language space, suffering from two major drawbacks: a) Their encoders only consider the sequential content of code, ignoring the tree structure which is also critical for the task of code summarization, b) Their decoders are typically trained to predict the next word by maximizing the likelihood of next ground-truth word with previous ground-truth word given. However, it is expected to generate the entire sequence from scratch at test time. This discrepancy can cause an \textit{exposure bias} issue, making the learnt decoder suboptimal. In this paper, we incorporate an abstract syntax tree structure as well as sequential content of code snippets into a deep reinforcement learning framework (i.e., actor-critic network). The actor network provides the confidence of predicting the next word according to current state. On the other hand, the critic network evaluates the reward value of all possible extensions of the current state and can provide global guidance for explorations. We employ an advantage reward composed of BLEU metric to train both networks. Comprehensive experiments on a real-world dataset show the effectiveness of our proposed model when compared with some state-of-the-art methods.

Yao Wan, Wenqiang Yan, Jianwei Gao et al.

Dialogue Act (DA) classification is a challenging problem in dialogue interpretation, which aims to attach semantic labels to utterances and characterize the speaker's intention. Currently, many existing approaches formulate the DA classification problem ranging from multi-classification to structured prediction, which suffer from two limitations: a) these methods are either handcrafted feature-based or have limited memories. b) adversarial examples can't be correctly classified by traditional training methods. To address these issues, in this paper we first cast the problem into a question and answering problem and proposed an improved dynamic memory networks with hierarchical pyramidal utterance encoder. Moreover, we apply adversarial training to train our proposed model. We evaluate our model on two public datasets, i.e., Switchboard dialogue act corpus and the MapTask corpus. Extensive experiments show that our proposed model is not only robust, but also achieves better performance when compared with some state-of-the-art baselines.

Jianguo Zhang, Pengcheng Zou, Zhao Li et al.

Nowadays, an increasing number of customers are in favor of using E-commerce Apps to browse and purchase products. Since merchants are usually inclined to employ redundant and over-informative product titles to attract customers' attention, it is of great importance to concisely display short product titles on limited screen of cell phones. Previous researchers mainly consider textual information of long product titles and lack of human-like view during training and evaluation procedure. In this paper, we propose a Multi-Modal Generative Adversarial Network (MM-GAN) for short product title generation, which innovatively incorporates image information, attribute tags from the product and the textual information from original long titles. MM-GAN treats short titles generation as a reinforcement learning process, where the generated titles are evaluated by the discriminator in a human-like view.