Seung-won Hwang

Seungjun Moon, Hyungjoo Chae, Yongho Song et al. · gatech

Code editing is an essential step towards reliable program synthesis to automatically correct critical errors generated from code LLMs. Recent studies have demonstrated that closed-source LLMs (i.e., ChatGPT and GPT-4) are capable of generating corrective feedback to edit erroneous inputs. However, it remains challenging for open-source code LLMs to generate feedback for code editing, since these models tend to adhere to the superficial formats of feedback and provide feedback with misleading information. Hence, the focus of our work is to leverage open-source code LLMs to generate helpful feedback with correct guidance for code editing. To this end, we present Coffee, a collected dataset specifically designed for code fixing with feedback. Using this dataset, we construct CoffeePots, a framework for COde Fixing with FEEdback via Preference-Optimized Tuning and Selection. The proposed framework aims to automatically generate helpful feedback for code editing while minimizing the potential risk of superficial feedback. The combination of Coffee and CoffeePots marks a significant advancement, achieving state-of-the-art performance on HumanEvalFix benchmark. Codes and model checkpoints are publicly available at https://github.com/Lune-Blue/COFFEE.

Hyungjoo Chae, Taeyoon Kwon, Seungjun Moon et al. · gatech

This paper presents Coffee-Gym, a comprehensive RL environment for training models that provide feedback on code editing. Coffee-Gym includes two major components: (1) Coffee, a dataset containing humans' code edit traces for coding questions and machine-written feedback for editing erroneous code; (2) CoffeeEval, a reward function that faithfully reflects the helpfulness of feedback by assessing the performance of the revised code in unit tests. With them, Coffee-Gym addresses the unavailability of high-quality datasets for training feedback models with RL, and provides more accurate rewards than the SOTA reward model (i.e., GPT-4). By applying Coffee-Gym, we elicit feedback models that outperform baselines in enhancing open-source code LLMs' code editing, making them comparable with closed-source LLMs. We make the dataset and the model checkpoint publicly available.

Yeonseok Jeong, Jinsu Kim, Dohyeon Lee et al.

Large Language Models (LLMs) have shown remarkable performance in Open-Domain Question Answering (ODQA) by leveraging external documents through Retrieval-Augmented Generation (RAG). To reduce RAG overhead, from longer context, context compression is necessary. However, prior compression methods do not focus on filtering out non-evidential information, which limit the performance in LLM-based RAG. We thus propose Evidentiality-guided RAG, or ECoRAG framework. ECoRAG improves LLM performance by compressing retrieved documents based on evidentiality, ensuring whether answer generation is supported by the correct evidence. As an additional step, ECoRAG reflects whether the compressed content provides sufficient evidence, and if not, retrieves more until sufficient. Experiments show that ECoRAG improves LLM performance on ODQA tasks, outperforming existing compression methods. Furthermore, ECoRAG is highly cost-efficient, as it not only reduces latency but also minimizes token usage by retaining only the necessary information to generate the correct answer. Code is available at https://github.com/ldilab/ECoRAG.

Kai Tzu-iunn Ong, Namyoung Kim, Minju Gwak et al.

To achieve lifelong human-agent interaction, dialogue agents need to constantly memorize perceived information and properly retrieve it for response generation (RG). While prior studies focus on getting rid of outdated memories to improve retrieval quality, we argue that such memories provide rich, important contextual cues for RG (e.g., changes in user behaviors) in long-term conversations. We present THEANINE, a framework for LLM-based lifelong dialogue agents. THEANINE discards memory removal and manages large-scale memories by linking them based on their temporal and cause-effect relation. Enabled by this linking structure, THEANINE augments RG with memory timelines - series of memories representing the evolution or causality of relevant past events. Along with THEANINE, we introduce TeaFarm, a counterfactual-driven evaluation scheme, addressing the limitation of G-Eval and human efforts when assessing agent performance in integrating past memories into RG. A supplementary video for THEANINE and data for TeaFarm are at https://huggingface.co/spaces/ResearcherScholar/Theanine.

Reinald Kim Amplayo, Seung-won Hwang, Min Song

Word sense induction (WSI), or the task of automatically discovering multiple senses or meanings of a word, has three main challenges: domain adaptability, novel sense detection, and sense granularity flexibility. While current latent variable models are known to solve the first two challenges, they are not flexible to different word sense granularities, which differ very much among words, from aardvark with one sense, to play with over 50 senses. Current models either require hyperparameter tuning or nonparametric induction of the number of senses, which we find both to be ineffective. Thus, we aim to eliminate these requirements and solve the sense granularity problem by proposing AutoSense, a latent variable model based on two observations: (1) senses are represented as a distribution over topics, and (2) senses generate pairings between the target word and its neighboring word. These observations alleviate the problem by (a) throwing garbage senses and (b) additionally inducing fine-grained word senses. Results show great improvements over the state-of-the-art models on popular WSI datasets. We also show that AutoSense is able to learn the appropriate sense granularity of a word. Finally, we apply AutoSense to the unsupervised author name disambiguation task where the sense granularity problem is more evident and show that AutoSense is evidently better than competing models. We share our data and code here: https://github.com/rktamplayo/AutoSense.

Ye Eun Chun, Sunjae Kwon, Kyunghwan Sohn et al.

In this paper, we introduce CR-COPEC called Causal Rationale of Corporate Performance Changes from financial reports. This is a comprehensive large-scale domain-adaptation causal sentence dataset to detect financial performance changes of corporate. CR-COPEC contributes to two major achievements. First, it detects causal rationale from 10-K annual reports of the U.S. companies, which contain experts' causal analysis following accounting standards in a formal manner. This dataset can be widely used by both individual investors and analysts as material information resources for investing and decision making without tremendous effort to read through all the documents. Second, it carefully considers different characteristics which affect the financial performance of companies in twelve industries. As a result, CR-COPEC can distinguish causal sentences in various industries by taking unique narratives in each industry into consideration. We also provide an extensive analysis of how well CR-COPEC dataset is constructed and suited for classifying target sentences as causal ones with respect to industry characteristics. Our dataset and experimental codes are publicly available.

Yeonseok Jeong, Minsoo Kim, Seung-won Hwang et al.

Large Language Models (LLMs) have demonstrated near-human performance in summarization tasks based on traditional metrics such as ROUGE and BERTScore. However, these metrics do not adequately capture critical aspects of summarization quality, such as factual accuracy, particularly for long narratives (>100K tokens). Recent advances, such as LLM-as-a-Judge, address the limitations of metrics based on lexical similarity but still exhibit factual inconsistencies, especially in understanding character relationships and states. In this work, we introduce NarrativeFactScore, a novel "Agent-as-a-Judge" framework for evaluating and refining summaries. By leveraging a Character Knowledge Graph (CKG) extracted from input and generated summaries, NarrativeFactScore assesses the factual consistency and provides actionable guidance for refinement, such as identifying missing or erroneous facts. We demonstrate the effectiveness of NarrativeFactScore through a detailed workflow illustration and extensive validation on widely adopted benchmarks, achieving superior performance compared to competitive methods. Our results highlight the potential of agent-driven evaluation systems to improve the factual reliability of LLM-generated summaries.

Jaeyoung Kim, Jongho Kim, Seung-won Hwang et al.

Retrieval-Augmented Generation systems often suffer from a gap between optimizing retrieval relevance and generative utility: retrieved documents may be topically relevant but still lack the content needed for effective reasoning during generation. While existing "bridge" modules attempt to rewrite the retrieved text for better generation, we show how they fail to capture true document utility. In this work, we propose R2U, with a key distinction of directly optimizing to maximize the probability of generating a correct answer through process supervision. As such direct observation is expensive, we also propose approximating an efficient distillation pipeline by scaling the supervision from LLMs, which helps the smaller rewriter model generalize better. We evaluate our method across multiple open-domain question-answering benchmarks. The empirical results demonstrate consistent improvements over strong bridging baselines.

Ye Eun Chun, Taeyoon Hwang, Seung-won Hwang et al.

Understanding complex character relations is crucial for narrative analysis and efficient script evaluation, yet existing extraction methods often fail to handle long-form narratives with nuanced interactions. To address this challenge, we present CREFT, a novel sequential framework leveraging specialized Large Language Model (LLM) agents. First, CREFT builds a base character graph through knowledge distillation, then iteratively refines character composition, relation extraction, role identification, and group assignments. Experiments on a curated Korean drama dataset demonstrate that CREFT significantly outperforms single-agent LLM baselines in both accuracy and completeness. By systematically visualizing character networks, CREFT streamlines narrative comprehension and accelerates script review -- offering substantial benefits to the entertainment, publishing, and educational sectors.

Soyoung Yoon, Gyuwan Kim, Gyu-Hwung Cho et al.

Listwise reranking with large language models (LLMs) enhances top-ranked results in retrieval-based applications. Due to the limit in context size and high inference cost of long context, reranking is typically performed over a fixed size of small subsets, with the final ranking aggregated from these partial results. This fixed computation disregards query difficulty and document distribution, leading to inefficiencies. We propose AcuRank, an adaptive reranking framework that dynamically adjusts both the amount and target of computation based on uncertainty estimates over document relevance. Using a Bayesian TrueSkill model, we iteratively refine relevance estimates until reaching sufficient confidence levels, and our explicit modeling of ranking uncertainty enables principled control over reranking behavior and avoids unnecessary updates to confident predictions. Results on the TREC-DL and BEIR benchmarks show that our method consistently achieves a superior accuracy-efficiency trade-off and scales better with compute than fixed-computation baselines. These results highlight the effectiveness and generalizability of our method across diverse retrieval tasks and LLM-based reranking models.

Shin-woo Park, Byung Jun Bae, Jinyoung Yeo et al.

Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved superior performance in tasks such as node classification. However, analyzing heterogeneous graph of different types of nodes and links still brings great challenges for injecting the heterogeneity into a graph neural network. A general remedy is to manually or automatically design meta-paths to transform a heterogeneous graph into a homogeneous graph, but this is suboptimal since the features from the first-order neighbors are not fully leveraged for training and inference. In this paper, we propose simple and effective graph neural networks for heterogeneous graph, excluding the use of meta-paths. Specifically, our models focus on relaxing the heterogeneity stress for model parameters by expanding model capacity of general GNNs in an effective way. Extensive experimental results on six real-world graphs not only show the superior performance of our proposed models over the state-of-the-arts, but also demonstrate the potentially good balance between reducing the heterogeneity stress and increasing the parameter size. Our code is freely available for reproducing our results.

Reinald Kim Amplayo, Seonjae Lim, Seung-won Hwang

Can a text classifier generalize well for datasets where the text length is different? For example, when short reviews are sentiment-labeled, can these transfer to predict the sentiment of long reviews (i.e., short to long transfer), or vice versa? While unsupervised transfer learning has been well-studied for cross domain/lingual transfer tasks, Cross Length Transfer (CLT) has not yet been explored. One reason is the assumption that length difference is trivially transferable in classification. We show that it is not, because short/long texts differ in context richness and word intensity. We devise new benchmark datasets from diverse domains and languages, and show that existing models from similar tasks cannot deal with the unique challenge of transferring across text lengths. We introduce a strong baseline model called BaggedCNN that treats long texts as bags containing short texts. We propose a state-of-the-art CLT model called Length Transfer Networks (LeTraNets) that introduces a two-way encoding scheme for short and long texts using multiple training mechanisms. We test our models and find that existing models perform worse than the BaggedCNN baseline, while LeTraNets outperforms all models.

Jihyeok Kim, Reinald Kim Amplayo, Kyungjae Lee et al.

The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user/product information for sentiment classification. These information have been used to modify parts of the model (e.g., word embeddings, attention mechanisms) such that results can be customized according to the metadata. We observe that current representation methods for categorical metadata, which are devised for human consumption, are not as effective as claimed in popular classification methods, outperformed even by simple concatenation of categorical features in the final layer of the sentence encoder. We conjecture that categorical features are harder to represent for machine use, as available context only indirectly describes the category, and even such context is often scarce (for tail category). To this end, we propose to use basis vectors to effectively incorporate categorical metadata on various parts of a neural-based model. This additionally decreases the number of parameters dramatically, especially when the number of categorical features is large. Extensive experiments on various datasets with different properties are performed and show that through our method, we can represent categorical metadata more effectively to customize parts of the model, including unexplored ones, and increase the performance of the model greatly.

Gyeongbok Lee, Sungdong Kim, Seung-won Hwang

Question answering (QA) extracting answers from text to the given question in natural language, has been actively studied and existing models have shown a promise of outperforming human performance when trained and evaluated with SQuAD dataset. However, such performance may not be replicated in the actual setting, for which we need to diagnose the cause, which is non-trivial due to the complexity of model. We thus propose a web-based UI that provides how each model contributes to QA performances, by integrating visualization and analysis tools for model explanation. We expect this framework can help QA model researchers to refine and improve their models.

Minseok Cho, Reinald Kim Amplayo, Seung-won Hwang et al.

The task of answering a question given a text passage has shown great developments on model performance thanks to community efforts in building useful datasets. Recently, there have been doubts whether such rapid progress has been based on truly understanding language. The same question has not been asked in the table question answering (TableQA) task, where we are tasked to answer a query given a table. We show that existing efforts, of using "answers" for both evaluation and supervision for TableQA, show deteriorating performances in adversarial settings of perturbations that do not affect the answer. This insight naturally motivates to develop new models that understand question and table more precisely. For this goal, we propose Neural Operator (NeOp), a multi-layer sequential network with attention supervision to answer the query given a table. NeOp uses multiple Selective Recurrent Units (SelRUs) to further help the interpretability of the answers of the model. Experiments show that the use of operand information to train the model significantly improves the performance and interpretability of TableQA models. NeOp outperforms all the previous models by a big margin.

Reinald Kim Amplayo, Seung-won Hwang

This paper aims at an aspect sentiment model for aspect-based sentiment analysis (ABSA) focused on micro reviews. This task is important in order to understand short reviews majority of the users write, while existing topic models are targeted for expert-level long reviews with sufficient co-occurrence patterns to observe. Current methods on aggregating micro reviews using metadata information may not be effective as well due to metadata absence, topical heterogeneity, and cold start problems. To this end, we propose a model called Micro Aspect Sentiment Model (MicroASM). MicroASM is based on the observation that short reviews 1) are viewed with sentiment-aspect word pairs as building blocks of information, and 2) can be clustered into larger reviews. When compared to the current state-of-the-art aspect sentiment models, experiments show that our model provides better performance on aspect-level tasks such as aspect term extraction and document-level tasks such as sentiment classification.

Wanyun Cui, Xiyou Zhou, Hangyu Lin et al.

Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs' roles. These roles are too coarse to represent verbs' semantics. In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb. First we analyze the principles for verb patterns: generality and specificity. Then we propose a nonparametric model based on description length. Experimental results prove the high effectiveness of verb patterns. We further apply verb patterns to context-aware conceptualization, to show that verb patterns are helpful in semantic-related tasks.