William Wang

Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou et al. · amazon-science, ibm-research

We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data. Our proposed method aims to improve performance in multi-task training, zero-shot and few-shot scenarios by providing a unified representation that can handle various forms of structured data such as tables, knowledge graph triples, and meaning representations. We demonstrate that our proposed approach can effectively adapt to new structured forms, and can improve performance in comparison to current methods. For example, our method resulted in a 66% improvement in zero-shot BLEU scores when transferring models trained on table inputs to a knowledge graph dataset. Our proposed method is an important step towards a more general data-to-text generation framework.

Danilo Ribeiro, Shen Wang, Xiaofei Ma et al. · amazon-science

We introduce STREET, a unified multi-task and multi-domain natural language reasoning and explanation benchmark. Unlike most existing question-answering (QA) datasets, we expect models to not only answer questions, but also produce step-by-step structured explanations describing how premises in the question are used to produce intermediate conclusions that can prove the correctness of a certain answer. We perform extensive evaluation with popular language models such as few-shot prompting GPT-3 and fine-tuned T5. We find that these models still lag behind human performance when producing such structured reasoning steps. We believe this work will provide a way for the community to better train and test systems on multi-step reasoning and explanations in natural language.

Percy Liang, Rishi Bommasani, Tony Lee et al. · stanford

Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models. First, we taxonomize the vast space of potential scenarios (i.e. use cases) and metrics (i.e. desiderata) that are of interest for LMs. Then we select a broad subset based on coverage and feasibility, noting what's missing or underrepresented (e.g. question answering for neglected English dialects, metrics for trustworthiness). Second, we adopt a multi-metric approach: We measure 7 metrics (accuracy, calibration, robustness, fairness, bias, toxicity, and efficiency) for each of 16 core scenarios when possible (87.5% of the time). This ensures metrics beyond accuracy don't fall to the wayside, and that trade-offs are clearly exposed. We also perform 7 targeted evaluations, based on 26 targeted scenarios, to analyze specific aspects (e.g. reasoning, disinformation). Third, we conduct a large-scale evaluation of 30 prominent language models (spanning open, limited-access, and closed models) on all 42 scenarios, 21 of which were not previously used in mainstream LM evaluation. Prior to HELM, models on average were evaluated on just 17.9% of the core HELM scenarios, with some prominent models not sharing a single scenario in common. We improve this to 96.0%: now all 30 models have been densely benchmarked on the same core scenarios and metrics under standardized conditions. Our evaluation surfaces 25 top-level findings. For full transparency, we release all raw model prompts and completions publicly for further analysis, as well as a general modular toolkit. We intend for HELM to be a living benchmark for the community, continuously updated with new scenarios, metrics, and models.

Donghan Yu, Sheng Zhang, Patrick Ng et al.

Question answering over knowledge bases (KBs) aims to answer natural language questions with factual information such as entities and relations in KBs. Previous methods either generate logical forms that can be executed over KBs to obtain final answers or predict answers directly. Empirical results show that the former often produces more accurate answers, but it suffers from non-execution issues due to potential syntactic and semantic errors in the generated logical forms. In this work, we propose a novel framework DecAF that jointly generates both logical forms and direct answers, and then combines the merits of them to get the final answers. Moreover, different from most of the previous methods, DecAF is based on simple free-text retrieval without relying on any entity linking tools -- this simplification eases its adaptation to different datasets. DecAF achieves new state-of-the-art accuracy on WebQSP, FreebaseQA, and GrailQA benchmarks, while getting competitive results on the ComplexWebQuestions benchmark.

An Yan, Yu Wang, Yiwu Zhong et al.

Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language models to classify images via these attributes. Pioneering work shows that querying thousands of attributes can achieve performance competitive with image features. However, our further investigation on 8 datasets reveals that LLM-generated attributes in a large quantity perform almost the same as random words. This surprising finding suggests that significant noise may be present in these attributes. We hypothesize that there exist subsets of attributes that can maintain the classification performance with much smaller sizes, and propose a novel learning-to-search method to discover those concise sets of attributes. As a result, on the CUB dataset, our method achieves performance close to that of massive LLM-generated attributes (e.g., 10k attributes for CUB), yet using only 32 attributes in total to distinguish 200 bird species. Furthermore, our new paradigm demonstrates several additional benefits: higher interpretability and interactivity for humans, and the ability to summarize knowledge for a recognition task.

Connor Pryor, Charles Dickens, Eriq Augustine et al.

In this paper, we introduce Neural Probabilistic Soft Logic (NeuPSL), a novel neuro-symbolic (NeSy) framework that unites state-of-the-art symbolic reasoning with the low-level perception of deep neural networks. To model the boundary between neural and symbolic representations, we propose a family of energy-based models, NeSy Energy-Based Models, and show that they are general enough to include NeuPSL and many other NeSy approaches. Using this framework, we show how to seamlessly integrate neural and symbolic parameter learning and inference in NeuPSL. Through an extensive empirical evaluation, we demonstrate the benefits of using NeSy methods, achieving upwards of 30% improvement over independent neural network models. On a well-established NeSy task, MNIST-Addition, NeuPSL demonstrates its joint reasoning capabilities by outperforming existing NeSy approaches by up to 10% in low-data settings. Furthermore, NeuPSL achieves a 5% boost in performance over state-of-the-art NeSy methods in a canonical citation network task with up to a 40 times speed up.

Xinyi Wu, Zhengdao Chen, William Wang et al.

Oversmoothing is a central challenge of building more powerful Graph Neural Networks (GNNs). While previous works have only demonstrated that oversmoothing is inevitable when the number of graph convolutions tends to infinity, in this paper, we precisely characterize the mechanism behind the phenomenon via a non-asymptotic analysis. Specifically, we distinguish between two different effects when applying graph convolutions -- an undesirable mixing effect that homogenizes node representations in different classes, and a desirable denoising effect that homogenizes node representations in the same class. By quantifying these two effects on random graphs sampled from the Contextual Stochastic Block Model (CSBM), we show that oversmoothing happens once the mixing effect starts to dominate the denoising effect, and the number of layers required for this transition is $O(\log N/\log (\log N))$ for sufficiently dense graphs with $N$ nodes. We also extend our analysis to study the effects of Personalized PageRank (PPR), or equivalently, the effects of initial residual connections on oversmoothing. Our results suggest that while PPR mitigates oversmoothing at deeper layers, PPR-based architectures still achieve their best performance at a shallow depth and are outperformed by the graph convolution approach on certain graphs. Finally, we support our theoretical results with numerical experiments, which further suggest that the oversmoothing phenomenon observed in practice can be magnified by the difficulty of optimizing deep GNN models.

Charles Dickens, Connor Pryor, Changyu Gao et al.

The field of Neural-Symbolic (NeSy) systems is growing rapidly. Proposed approaches show great promise in achieving symbiotic unions of neural and symbolic methods. However, a unifying framework is needed to organize common NeSy modeling patterns and develop general learning approaches. In this paper, we introduce Neural-Symbolic Energy-Based Models (NeSy-EBMs), a unifying mathematical framework for discriminative and generative NeSy modeling. Importantly, NeSy-EBMs allow the derivation of general expressions for gradients of prominent learning losses, and we introduce a suite of four learning approaches that leverage methods from multiple domains, including bilevel and stochastic policy optimization. Finally, we ground the NeSy-EBM framework with Neural Probabilistic Soft Logic (NeuPSL), an open-source NeSy-EBM library designed for scalability and expressivity, facilitating the real-world application of NeSy systems. Through extensive empirical analysis across multiple datasets, we demonstrate the practical advantages of NeSy-EBMs in various tasks, including image classification, graph node labeling, autonomous vehicle situation awareness, and question answering.

Eriq Augustine, Pegah Jandaghi, Alon Albalak et al.

Creating agents that can both appropriately respond to conversations and understand complex human linguistic tendencies and social cues has been a long standing challenge in the NLP community. A recent pillar of research revolves around emotion recognition in conversation (ERC); a sub-field of emotion recognition that focuses on conversations or dialogues that contain two or more utterances. In this work, we explore an approach to ERC that exploits the use of neural embeddings along with complex structures in dialogues. We implement our approach in a framework called Probabilistic Soft Logic (PSL), a declarative templating language that uses first-order like logical rules, that when combined with data, define a particular class of graphical model. Additionally, PSL provides functionality for the incorporation of results from neural models into PSL models. This allows our model to take advantage of advanced neural methods, such as sentence embeddings, and logical reasoning over the structure of a dialogue. We compare our method with state-of-the-art purely neural ERC systems, and see almost a 20% improvement. With these results, we provide an extensive qualitative and quantitative analysis over the DailyDialog conversation dataset.

Edwin Zhang, Yujie Lu, Shinda Huang et al.

Training generalist agents is difficult across several axes, requiring us to deal with high-dimensional inputs (space), long horizons (time), and generalization to novel tasks. Recent advances with architectures have allowed for improved scaling along one or two of these axes, but are still computationally prohibitive to use. In this paper, we propose to address all three axes by leveraging \textbf{L}anguage to \textbf{C}ontrol \textbf{D}iffusion models as a hierarchical planner conditioned on language (LCD). We effectively and efficiently scale diffusion models for planning in extended temporal, state, and task dimensions to tackle long horizon control problems conditioned on natural language instructions, as a step towards generalist agents. Comparing LCD with other state-of-the-art models on the CALVIN language robotics benchmark finds that LCD outperforms other SOTA methods in multi-task success rates, whilst improving inference speed over other comparable diffusion models by 3.3x~15x. We show that LCD can successfully leverage the unique strength of diffusion models to produce coherent long range plans while addressing their weakness in generating low-level details and control.

Yue Huang, Lichao Sun, Haoran Wang et al.

Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness.

Antonis Antoniades, Albert Örwall, Kexun Zhang et al.

Software engineers operating in complex and dynamic environments must continuously adapt to evolving requirements, learn iteratively from experience, and reconsider their approaches based on new insights. However, current large language model (LLM)-based software agents often follow linear, sequential processes that prevent backtracking and exploration of alternative solutions, limiting their ability to rethink their strategies when initial approaches prove ineffective. To address these challenges, we propose SWE-Search, a multi-agent framework that integrates Monte Carlo Tree Search (MCTS) with a self-improvement mechanism to enhance software agents' performance on repository-level software tasks. SWE-Search extends traditional MCTS by incorporating a hybrid value function that leverages LLMs for both numerical value estimation and qualitative evaluation. This enables self-feedback loops where agents iteratively refine their strategies based on both quantitative numerical evaluations and qualitative natural language assessments of pursued trajectories. The framework includes a SWE-Agent for adaptive exploration, a Value Agent for iterative feedback, and a Discriminator Agent that facilitates multi-agent debate for collaborative decision-making. Applied to the SWE-bench benchmark, our approach demonstrates a 23% relative improvement in performance across five models compared to standard open-source agents without MCTS. Our analysis reveals how performance scales with increased inference-time compute through deeper search, providing a pathway to improve software agents without requiring larger models or additional training data. This highlights the potential of self-evaluation driven search techniques in complex software engineering environments.

Antonis Antoniades, Yiyi Yu, Joseph Canzano et al.

State-of-the-art systems neuroscience experiments yield large-scale multimodal data, and these data sets require new tools for analysis. Inspired by the success of large pretrained models in vision and language domains, we reframe the analysis of large-scale, cellular-resolution neuronal spiking data into an autoregressive spatiotemporal generation problem. Neuroformer is a multimodal, multitask generative pretrained transformer (GPT) model that is specifically designed to handle the intricacies of data in systems neuroscience. It scales linearly with feature size, can process an arbitrary number of modalities, and is adaptable to downstream tasks, such as predicting behavior. We first trained Neuroformer on simulated datasets, and found that it both accurately predicted simulated neuronal circuit activity, and also intrinsically inferred the underlying neural circuit connectivity, including direction. When pretrained to decode neural responses, the model predicted the behavior of a mouse with only few-shot fine-tuning, suggesting that the model begins learning how to do so directly from the neural representations themselves, without any explicit supervision. We used an ablation study to show that joint training on neuronal responses and behavior boosted performance, highlighting the model's ability to associate behavioral and neural representations in an unsupervised manner. These findings show that Neuroformer can analyze neural datasets and their emergent properties, informing the development of models and hypotheses associated with the brain.

Wenyue Hua, Ollie Liu, Lingyao Li et al.

This paper investigates the rationality of large language models (LLMs) in strategic decision-making contexts, specifically within the framework of game theory. We evaluate several state-of-the-art LLMs across a spectrum of complete-information and incomplete-information games. Our findings reveal that LLMs frequently deviate from rational strategies, particularly as the complexity of the game increases with larger payoff matrices or deeper sequential trees. To address these limitations, we design multiple game-theoretic workflows that guide the reasoning and decision-making processes of LLMs. These workflows aim to enhance the models' ability to compute Nash Equilibria and make rational choices, even under conditions of uncertainty and incomplete information. Experimental results demonstrate that the adoption of these workflows significantly improves the rationality and robustness of LLMs in game-theoretic tasks. Specifically, with the workflow, LLMs exhibit marked improvements in identifying optimal strategies, achieving near-optimal allocations in negotiation scenarios, and reducing susceptibility to exploitation during negotiations. Furthermore, we explore the meta-strategic considerations of whether it is rational for agents to adopt such workflows, recognizing that the decision to use or forgo the workflow constitutes a game-theoretic issue in itself. Our research contributes to a deeper understanding of LLMs' decision-making capabilities in strategic contexts and provides insights into enhancing their rationality through structured workflows. The findings have implications for the development of more robust and strategically sound AI agents capable of navigating complex interactive environments. Code and data supporting this study are available at \url{https://github.com/Wenyueh/game_theory}.

Kexun Zhang, Hongqiao Chen, Lei Li et al.

Instruction-tuned large language models (LLMs) excel at many tasks but often fail to use external tools due to complicated and unfamiliar syntax constraints. While extensive fine-tuning and prompting can mitigate the issue, these approaches are expensive and hard to generalize. Furthermore, because syntax constraints are only learned implicitly during fine-tuning, models still make frequent syntax errors. Motivated by the fact that these constraints can be better satisfied explicitly with constrained decoding, we propose TOOLDEC, a decoding algorithm using finite state machines to force LLMs to follow tool syntax. Our experiments show that TOOLDEC eliminates all syntax errors, achieving significantly better performance on various base models and benchmarks. More surprisingly, when applied to generalist out-of-the-box LLMs such as Mistral-Instruct, TOOLDEC improves its accuracy in tool use from the initial 0% to an impressive 52%, matching the performance of specialized fine-tuned models such as ToolLLM.

Alfonso Amayuelas, Firas Laakom, Piotr Piękos et al.

The use of LLMs for code generation has naturally extended to code testing and evaluation. As codebases grow in size and complexity, so does the need for automated test generation. Current approaches for LLM-based test generation rely on strategies that maximize immediate coverage gain, a greedy approach that plateaus on code where reaching deep branches requires setup steps that individually yield zero new coverage. Drawing on principles of Bayesian exploration, we treat the program's branch structure as an unknown environment, and an evolving coverage map as a proxy probabilistic posterior representing what the LLM has discovered so far. Our method, CovQValue, feeds the coverage map back to the LLM, generates diverse candidate plans in parallel, and selects the most informative plan by LLM-estimated Q-values, seeking actions that balance immediate branch discovery with future reachability. Our method outperforms greedy selection on TestGenEval Lite, achieving 51-77% higher branch coverage across three popular LLMs and winning on 77-84% of targets. In addition, we build a benchmark for iterative test generation, RepoExploreBench, where they achieve 40-74%. These results show the potential of curiosity-driven planning methods for LLM-based exploration, enabling more effective discovery of program behavior through sequential interaction

Alfonso Amayuelas, Kyle Wong, Liangming Pan et al.

This paper investigates the capabilities of Large Language Models (LLMs) in the context of understanding their knowledge and uncertainty over questions. Specifically, we focus on addressing known-unknown questions, characterized by high uncertainty due to the absence of definitive answers. To facilitate our study, we collect a new dataset with Known-Unknown Questions (KUQ) and establish a categorization framework to clarify the origins of uncertainty in such queries. Subsequently, we examine the performance of open-source LLMs, fine-tuned using this dataset, in distinguishing between known and unknown queries within open-ended question-answering scenarios. The fine-tuned models demonstrated a significant improvement, achieving a considerable increase in F1-score relative to their pre-fine-tuning state. Through a comprehensive analysis, we reveal insights into the models' improved uncertainty articulation and their consequent efficacy in multi-agent debates. These findings help us understand how LLMs can be trained to identify and express uncertainty, improving our knowledge of how they understand and express complex or unclear information.

Wenhu Chen, Hanwen Zha, Zhiyu Chen et al.

Existing question answering datasets focus on dealing with homogeneous information, based either only on text or KB/Table information alone. However, as human knowledge is distributed over heterogeneous forms, using homogeneous information alone might lead to severe coverage problems. To fill in the gap, we present HybridQA https://github.com/wenhuchen/HybridQA, a new large-scale question-answering dataset that requires reasoning on heterogeneous information. Each question is aligned with a Wikipedia table and multiple free-form corpora linked with the entities in the table. The questions are designed to aggregate both tabular information and text information, i.e., lack of either form would render the question unanswerable. We test with three different models: 1) a table-only model. 2) text-only model. 3) a hybrid model that combines heterogeneous information to find the answer. The experimental results show that the EM scores obtained by two baselines are below 20\%, while the hybrid model can achieve an EM over 40\%. This gap suggests the necessity to aggregate heterogeneous information in HybridQA. However, the hybrid model's score is still far behind human performance. Hence, HybridQA can serve as a challenging benchmark to study question answering with heterogeneous information.

Wenhu Chen, Zhe Gan, Linjie Li et al.

Neural Module Network (NMN) exhibits strong interpretability and compositionality thanks to its handcrafted neural modules with explicit multi-hop reasoning capability. However, most NMNs suffer from two critical drawbacks: 1) scalability: customized module for specific function renders it impractical when scaling up to a larger set of functions in complex tasks; 2) generalizability: rigid pre-defined module inventory makes it difficult to generalize to unseen functions in new tasks/domains. To design a more powerful NMN architecture for practical use, we propose Meta Module Network (MMN) centered on a novel meta module, which can take in function recipes and morph into diverse instance modules dynamically. The instance modules are then woven into an execution graph for complex visual reasoning, inheriting the strong explainability and compositionality of NMN. With such a flexible instantiation mechanism, the parameters of instance modules are inherited from the central meta module, retaining the same model complexity as the function set grows, which promises better scalability. Meanwhile, as functions are encoded into the embedding space, unseen functions can be readily represented based on its structural similarity with previously observed ones, which ensures better generalizability. Experiments on GQA and CLEVR datasets validate the superiority of MMN over state-of-the-art NMN designs. Synthetic experiments on held-out unseen functions from GQA dataset also demonstrate the strong generalizability of MMN. Our code and model are released in Github https://github.com/wenhuchen/Meta-Module-Network.

Minglai Yang, Ethan Huang, Liang Zhang et al.

We introduce Grade School Math with Distracting Context (GSM-DC), a synthetic benchmark to evaluate Large Language Models' (LLMs) reasoning robustness against systematically controlled irrelevant context (IC). GSM-DC constructs symbolic reasoning graphs with precise distractor injections, enabling rigorous, reproducible evaluation. Our experiments demonstrate that LLMs are significantly sensitive to IC, affecting both reasoning path selection and arithmetic accuracy. Additionally, training models with strong distractors improves performance in both in-distribution and out-of-distribution scenarios. We further propose a stepwise tree search guided by a process reward model, which notably enhances robustness in out-of-distribution conditions.

Nikolas Belle, Dakota Barnes, Alfonso Amayuelas et al.

We address the long-horizon gap in large language model (LLM) agents by enabling them to sustain coherent strategies in adversarial, stochastic environments. Settlers of Catan provides a challenging benchmark: success depends on balancing short- and long-term goals amid randomness, trading, expansion, and blocking. Prompt-centric LLM agents (e.g., ReAct, Reflexion) must re-interpret large, evolving game states each turn, quickly saturating context windows and losing strategic consistency. We propose HexMachina, a continual learning multi-agent system that separates environment discovery (inducing an adapter layer without documentation) from strategy improvement (evolving a compiled player through code refinement and simulation). This design preserves executable artifacts, allowing the LLM to focus on high-level strategy rather than per-turn reasoning. In controlled Catanatron experiments, HexMachina learns from scratch and evolves players that outperform the strongest human-crafted baseline (AlphaBeta), achieving a 54% win rate and surpassing prompt-driven and no-discovery baselines. Ablations confirm that isolating pure strategy learning improves performance. Overall, artifact-centric continual learning transforms LLMs from brittle stepwise deciders into stable strategy designers, advancing long-horizon autonomy.

Alfonso Amayuelas, Jingbo Yang, Saaket Agashe et al.

With the development of LLMs as agents, there is a growing interest in connecting multiple agents into multi-agent systems to solve tasks concurrently, focusing on their role in task assignment and coordination. This paper explores how LLMs can effectively allocate computational tasks among multiple agents, considering factors such as cost, efficiency, and performance. In this work, we address key questions, including the effectiveness of LLMs as orchestrators and planners, comparing their effectiveness in task assignment and coordination. Our experiments demonstrate that LLMs can achieve high validity and accuracy in resource allocation tasks. We find that the planner method outperforms the orchestrator method in handling concurrent actions, resulting in improved efficiency and better utilization of agents. Additionally, we show that providing explicit information about worker capabilities enhances the allocation strategies of planners, particularly when dealing with suboptimal workers.

Rui Huang, Binbin Jiang, Qingyi Zhao et al.

In this work, we aim to detect the changes caused by object variations in a scene represented by the neural radiance fields (NeRFs). Given an arbitrary view and two sets of scene images captured at different timestamps, we can predict the scene changes in that view, which has significant potential applications in scene monitoring and measuring. We conducted preliminary studies and found that such an exciting task cannot be easily achieved by utilizing existing NeRFs and 2D change detection methods with many false or missing detections. The main reason is that the 2D change detection is based on the pixel appearance difference between spatial-aligned image pairs and neglects the stereo information in the NeRF. To address the limitations, we propose the C-NERF to represent scene changes as directional consistency difference-based NeRF, which mainly contains three modules. We first perform the spatial alignment of two NeRFs captured before and after changes. Then, we identify the change points based on the direction-consistent constraint; that is, real change points have similar change representations across view directions, but fake change points do not. Finally, we design the change map rendering process based on the built NeRFs and can generate the change map of an arbitrarily specified view direction. To validate the effectiveness, we build a new dataset containing ten scenes covering diverse scenarios with different changing objects. Our approach surpasses state-of-the-art 2D change detection and NeRF-based methods by a significant margin.

Yujie Lu, Yale Song, William Wang et al.

We investigate complex video question answering via chain-of-evidence reasoning -- identifying sequences of temporal spans from multiple relevant parts of the video, together with visual evidence within them. Existing models struggle with multi-step reasoning as they uniformly sample a fixed number of frames, which can miss critical evidence distributed nonuniformly throughout the video. Moreover, they lack the ability to temporally localize such evidence in the broader context of the full video, which is required for answering complex questions. We propose a framework to enhance existing VideoQA datasets with evidence reasoning chains, automatically constructed by searching for optimal intervals of interest in the video with supporting evidence, that maximizes the likelihood of answering a given question. We train our model (VITED) to generate these evidence chains directly, enabling it to both localize evidence windows as well as perform multi-step reasoning across them in long-form video content. We show the value of our evidence-distilled models on a suite of long video QA benchmarks where we outperform state-of-the-art approaches that lack evidence reasoning capabilities.

Alfonso Amayuelas, Xianjun Yang, Antonis Antoniades et al.

Large Language Models (LLMs) have shown exceptional results on current benchmarks when working individually. The advancement in their capabilities, along with a reduction in parameter size and inference times, has facilitated the use of these models as agents, enabling interactions among multiple models to execute complex tasks. Such collaborations offer several advantages, including the use of specialized models (e.g. coding), improved confidence through multiple computations, and enhanced divergent thinking, leading to more diverse outputs. Thus, the collaborative use of language models is expected to grow significantly in the coming years. In this work, we evaluate the behavior of a network of models collaborating through debate under the influence of an adversary. We introduce pertinent metrics to assess the adversary's effectiveness, focusing on system accuracy and model agreement. Our findings highlight the importance of a model's persuasive ability in influencing others. Additionally, we explore inference-time methods to generate more compelling arguments and evaluate the potential of prompt-based mitigation as a defensive strategy.

Sijia Wang, Alexander Hanbo Li, Henry Zhu et al.

Entities can be expressed in diverse formats, such as texts, images, or column names and cell values in tables. While existing entity linking (EL) models work well on per modality configuration, such as text-only EL, visual grounding, or schema linking, it is more challenging to design a unified model for diverse modality configurations. To bring various modality configurations together, we constructed a benchmark for diverse-modal EL (DMEL) from existing EL datasets, covering all three modalities including text, image, and table. To approach the DMEL task, we proposed a generative diverse-modal model (GDMM) following a multimodal-encoder-decoder paradigm. Pre-training \Model with rich corpora builds a solid foundation for DMEL without storing the entire KB for inference. Fine-tuning GDMM builds a stronger DMEL baseline, outperforming state-of-the-art task-specific EL models by 8.51 F1 score on average. Additionally, extensive error analyses are conducted to highlight the challenges of DMEL, facilitating future research on this task.

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli et al.

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.

Wenhu Chen, Ming-Wei Chang, Eva Schlinger et al.

In open question answering (QA), the answer to a question is produced by retrieving and then analyzing documents that might contain answers to the question. Most open QA systems have considered only retrieving information from unstructured text. Here we consider for the first time open QA over both tabular and textual data and present a new large-scale dataset Open Table-and-Text Question Answering (OTT-QA) to evaluate performance on this task. Most questions in OTT-QA require multi-hop inference across tabular data and unstructured text, and the evidence required to answer a question can be distributed in different ways over these two types of input, making evidence retrieval challenging -- our baseline model using an iterative retriever and BERT-based reader achieves an exact match score less than 10%. We then propose two novel techniques to address the challenge of retrieving and aggregating evidence for OTT-QA. The first technique is to use "early fusion" to group multiple highly relevant tabular and textual units into a fused block, which provides more context for the retriever to search for. The second technique is to use a cross-block reader to model the cross-dependency between multiple retrieved evidence with global-local sparse attention. Combining these two techniques improves the score significantly, to above 27%.

Farzan Farnia, William Wang, Subhro Das et al.

Generative adversarial networks (GANs) learn the distribution of observed samples through a zero-sum game between two machine players, a generator and a discriminator. While GANs achieve great success in learning the complex distribution of image, sound, and text data, they perform suboptimally in learning multi-modal distribution-learning benchmarks including Gaussian mixture models (GMMs). In this paper, we propose Generative Adversarial Training for Gaussian Mixture Models (GAT-GMM), a minimax GAN framework for learning GMMs. Motivated by optimal transport theory, we design the zero-sum game in GAT-GMM using a random linear generator and a softmax-based quadratic discriminator architecture, which leads to a non-convex concave minimax optimization problem. We show that a Gradient Descent Ascent (GDA) method converges to an approximate stationary minimax point of the GAT-GMM optimization problem. In the benchmark case of a mixture of two symmetric, well-separated Gaussians, we further show this stationary point recovers the true parameters of the underlying GMM. We numerically support our theoretical findings by performing several experiments, which demonstrate that GAT-GMM can perform as well as the expectation-maximization algorithm in learning mixtures of two Gaussians.

Hong Wang, Christfried Focke, Rob Sylvester et al.

Modelling relations between multiple entities has attracted increasing attention recently, and a new dataset called DocRED has been collected in order to accelerate the research on the document-level relation extraction. Current baselines for this task uses BiLSTM to encode the whole document and are trained from scratch. We argue that such simple baselines are not strong enough to model to complex interaction between entities. In this paper, we further apply a pre-trained language model (BERT) to provide a stronger baseline for this task. We also find that solving this task in phases can further improve the performance. The first step is to predict whether or not two entities have a relation, the second step is to predict the specific relation.

Wenhu Chen, Yu Su, Yilin Shen et al.

With the rapid development in deep learning, deep neural networks have been widely adopted in many real-life natural language applications. Under deep neural networks, a pre-defined vocabulary is required to vectorize text inputs. The canonical approach to select pre-defined vocabulary is based on the word frequency, where a threshold is selected to cut off the long tail distribution. However, we observed that such simple approach could easily lead to under-sized vocabulary or over-sized vocabulary issues. Therefore, we are interested in understanding how the end-task classification accuracy is related to the vocabulary size and what is the minimum required vocabulary size to achieve a specific performance. In this paper, we provide a more sophisticated variational vocabulary dropout (VVD) based on variational dropout to perform vocabulary selection, which can intelligently select the subset of the vocabulary to achieve the required performance. To evaluate different algorithms on the newly proposed vocabulary selection problem, we propose two new metrics: Area Under Accuracy-Vocab Curve and Vocab Size under X\% Accuracy Drop. Through extensive experiments on various NLP classification tasks, our variational framework is shown to significantly outperform the frequency-based and other selection baselines on these metrics.

Weilin Cong, William Wang, Wang-Chien Lee

Despite the great success object detection and segmentation models have achieved in recognizing individual objects in images, performance on cognitive tasks such as image caption, semantic image retrieval, and visual QA is far from satisfactory. To achieve better performance on these cognitive tasks, merely recognizing individual object instances is insufficient. Instead, the interactions between object instances need to be captured in order to facilitate reasoning and understanding of the visual scenes in an image. Scene graph, a graph representation of images that captures object instances and their relationships, offers a comprehensive understanding of an image. However, existing techniques on scene graph generation fail to distinguish subjects and objects in the visual scenes of images and thus do not perform well with real-world datasets where exist ambiguous object instances. In this work, we propose a novel scene graph generation model for predicting object instances and its corresponding relationships in an image. Our model, SG-CRF, learns the sequential order of subject and object in a relationship triplet, and the semantic compatibility of object instance nodes and relationship nodes in a scene graph efficiently. Experiments empirically show that SG-CRF outperforms the state-of-the-art methods, on three different datasets, i.e., CLEVR, VRD, and Visual Genome, raising the Recall@100 from 24.99% to 49.95%, from 41.92% to 50.47%, and from 54.69% to 54.77%, respectively.

Wenhu Chen, Yilin Shen, Hongxia Jin et al.

With the recently rapid development in deep learning, deep neural networks have been widely adopted in many real-life applications. However, deep neural networks are also known to have very little control over its uncertainty for unseen examples, which potentially causes very harmful and annoying consequences in practical scenarios. In this paper, we are particularly interested in designing a higher-order uncertainty metric for deep neural networks and investigate its effectiveness under the out-of-distribution detection task proposed by~\cite{hendrycks2016baseline}. Our method first assumes there exists an underlying higher-order distribution $\mathbb{P}(z)$, which controls label-wise categorical distribution $\mathbb{P}(y)$ over classes on the K-dimension simplex, and then approximate such higher-order distribution via parameterized posterior function $p_θ(z|x)$ under variational inference framework, finally we use the entropy of learned posterior distribution $p_θ(z|x)$ as uncertainty measure to detect out-of-distribution examples. Further, we propose an auxiliary objective function to discriminate against synthesized adversarial examples to further increase the robustness of the proposed uncertainty measure. Through comprehensive experiments on various datasets, our proposed framework is demonstrated to consistently outperform competing algorithms.

Hao Yu, Vivek Kulkarni, William Wang

Many knowledge graph embedding methods operate on triples and are therefore implicitly limited by a very local view of the entire knowledge graph. We present a new framework MOHONE to effectively model higher order network effects in knowledge-graphs, thus enabling one to capture varying degrees of network connectivity (from the local to the global). Our framework is generic, explicitly models the network scale, and captures two different aspects of similarity in networks: (a) shared local neighborhood and (b) structural role-based similarity. First, we introduce methods that learn network representations of entities in the knowledge graph capturing these varied aspects of similarity. We then propose a fast, efficient method to incorporate the information captured by these network representations into existing knowledge graph embeddings. We show that our method consistently and significantly improves the performance on link prediction of several different knowledge-graph embedding methods including TRANSE, TRANSD, DISTMULT, and COMPLEX(by at least 4 points or 17% in some cases).

Wenhu Chen, Wenhan Xiong, Xifeng Yan et al.

Inferring missing links in knowledge graphs (KG) has attracted a lot of attention from the research community. In this paper, we tackle a practical query answering task involving predicting the relation of a given entity pair. We frame this prediction problem as an inference problem in a probabilistic graphical model and aim at resolving it from a variational inference perspective. In order to model the relation between the query entity pair, we assume that there exists an underlying latent variable (paths connecting two nodes) in the KG, which carries the equivalent semantics of their relations. However, due to the intractability of connections in large KGs, we propose to use variation inference to maximize the evidence lower bound. More specifically, our framework (\textsc{Diva}) is composed of three modules, i.e. a posterior approximator, a prior (path finder), and a likelihood (path reasoner). By using variational inference, we are able to incorporate them closely into a unified architecture and jointly optimize them to perform KG reasoning. With active interactions among these sub-modules, \textsc{Diva} is better at handling noise and coping with more complex reasoning scenarios. In order to evaluate our method, we conduct the experiment of the link prediction task on multiple datasets and achieve state-of-the-art performances on both datasets.

William Wang, Angelina Wang, Aviv Tamar et al.

The discriminative approach to classification using deep neural networks has become the de-facto standard in various fields. Complementing recent reservations about safety against adversarial examples, we show that conventional discriminative methods can easily be fooled to provide incorrect labels with very high confidence to out of distribution examples. We posit that a generative approach is the natural remedy for this problem, and propose a method for classification using generative models. At training time, we learn a generative model for each class, while at test time, given an example to classify, we query each generator for its most similar generation, and select the class corresponding to the most similar one. Our approach is general and can be used with expressive models such as GANs and VAEs. At test time, our method accurately "knows when it does not know," and provides resilience to out of distribution examples while maintaining competitive performance for standard examples.