Publications (277)
Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets
Vatsal Gupta, Pranshu Pandya, Tushar Kataria +2
Language models, characterized by their black-box nature, often hallucinate and display sensitivity to input perturbations, causing concerns about trust. To enhance trust, it is im…
Solving Hard Coreference Problems
Haoruo Peng, Daniel Khashabi, Dan Roth
Coreference resolution is a key problem in natural language understanding that still escapes reliable solutions. One fundamental difficulty has been that of resolving instances inv…
OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning
Marianne Menglin Liu, Sai Ashish Somayajula, Syed Fahad Allam Shah +2
We present OraPlan-SQL, our system for the Archer NL2SQL Evaluation Challenge 2025, a bilingual benchmark requiring complex reasoning such as arithmetic, commonsense, and hypotheti…
PRAISE: Enhancing Product Descriptions with LLM-Driven Structured Insights
Adnan Qidwai, Srija Mukhopadhyay, Prerana Khatiwada +2
Accurate and complete product descriptions are crucial for e-commerce, yet seller-provided information often falls short. Customer reviews offer valuable details but are laborious…
Do Language Embeddings Capture Scales?
Xikun Zhang, Deepak Ramachandran, Ian Tenney +2
Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense, and factual knowledge. One form of knowledge that has not been studied yet in this…
Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou +9
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…
LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval
William Bruno, Dan Roth
Natural language inference has trended toward studying contexts beyond the sentence level. An important application area is law: past cases often do not foretell how they apply to…
Cross-modal Map Learning for Vision and Language Navigation
Georgios Georgakis, Karl Schmeckpeper, Karan Wanchoo +4
We consider the problem of Vision-and-Language Navigation (VLN). The majority of current methods for VLN are trained end-to-end using either unstructured memory such as LSTM, or us…
Is Code Better Than Language for Algorithmic Reasoning
Terry Tong, Yu Feng, Surbhi Goel +1
For tool-augmented language models, comparing natural-language reasoning with code-execution pipelines is difficult because the comparison changes both the intermediate representat…
Multi-lingual Evaluation of Code Generation Models
Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang +22
We present new benchmarks on evaluation code generation models: MBXP and Multilingual HumanEval, and MathQA-X. These datasets cover over 10 programming languages and are generated…
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
Fei Wang, Xingyu Fu, James Y. Huang +18
We introduce MuirBench, a comprehensive benchmark that focuses on robust multi-image understanding capabilities of multimodal LLMs. MuirBench consists of 12 diverse multi-image tas…
ConflictScore: Identifying and Measuring How Language Models Handle Conflicting Evidence
Siyi Liu, Aaron Halfaker, Dan Roth +1
Existing metrics for factuality and faithfulness evaluate whether an answer is supported or contradicted by its grounding documents, but they fail to capture when both supporting a…
Conflicts in Texts: Data, Implications and Challenges
Siyi Liu, Dan Roth
As NLP models become increasingly integrated into real-world applications, it becomes clear that there is a need to address the fact that models often rely on and generate conflict…
Privacy Adhering Machine Un-learning in NLP
Vinayshekhar Bannihatti Kumar, Rashmi Gangadharaiah, Dan Roth
Regulations introduced by General Data Protection Regulation (GDPR) in the EU or California Consumer Privacy Act (CCPA) in the US have included provisions on the \textit{right to b…
CORE-T: COherent REtrieval of Tables for Text-to-SQL
Hassan Soliman, Vivek Gupta, Dan Roth +1
Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes a key bottleneck for end-to-end perform…
There is a Time and Place for Reasoning Beyond the Image
Xingyu Fu, Ben Zhou, Ishaan Preetam Chandratreya +2
Images are often more significant than only the pixels to human eyes, as we can infer, associate, and reason with contextual information from other sources to establish a more comp…
Distributed Training of Structured SVM
Ching-pei Lee, Kai-Wei Chang, Shyam Upadhyay +1
Training structured prediction models is time-consuming. However, most existing approaches only use a single machine, thus, the advantage of computing power and the capacity for la…
Term Definitions Help Hypernymy Detection
Wenpeng Yin, Dan Roth
Existing methods of hypernymy detection mainly rely on statistics over a big corpus, either mining some co-occurring patterns like "animals such as cats" or embedding words of inte…
Cross-lingual Models of Word Embeddings: An Empirical Comparison
Shyam Upadhyay, Manaal Faruqui, Chris Dyer +1
Despite interest in using cross-lingual knowledge to learn word embeddings for various tasks, a systematic comparison of the possible approaches is lacking in the literature. We pe…
MultiOpEd: A Corpus of Multi-Perspective News Editorials
Siyi Liu, Sihao Chen, Xander Uyttendaele +1
We propose MultiOpEd, an open-domain news editorial corpus that supports various tasks pertaining to the argumentation structure in news editorials, focusing on automatic perspecti…
NTSEBENCH: Cognitive Reasoning Benchmark for Vision Language Models
Pranshu Pandya, Vatsal Gupta, Agney S Talwarr +3
Cognitive textual and visual reasoning tasks, including puzzles, series, and analogies, demand the ability to quickly reason, decipher, and evaluate patterns both textually and spa…
Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts
Ben Zhou, Kyle Richardson, Xiaodong Yu +1
Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in devel…
Joint Reasoning for Temporal and Causal Relations
Qiang Ning, Zhili Feng, Hao Wu +1
Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must be before its effect in time, temporal and cau…
Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale
Hritik Bansal, Karthik Gopalakrishnan, Saket Dingliwal +3
Language models have been shown to perform better with an increase in scale on a wide variety of tasks via the in-context learning paradigm. In this paper, we investigate the hypot…
Code Representation Learning At Scale
Dejiao Zhang, Wasi Ahmad, Ming Tan +5
Recent studies have shown that code language models at scale demonstrate significant performance gains on downstream tasks, i.e., code generation. However, most of the existing wor…
AUTOCT: Automating Interpretable Clinical Trial Prediction with LLM Agents
Fengze Liu, Haoyu Wang, Joonhyuk Cho +2
Clinical trials are critical for advancing medical treatments but remain prohibitively expensive and time-consuming. Accurate prediction of clinical trial outcomes can significantl…
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
Uri Alon, Frank F. Xu, Junxian He +3
Retrieval-based language models (R-LM) model the probability of natural language text by combining a standard language model (LM) with examples retrieved from an external datastore…
From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification
Fei Wang, Chao Shang, Sarthak Jain +6
User alignment is crucial for adapting general-purpose language models (LMs) to downstream tasks, but human annotations are often not available for all types of instructions, espec…
Applying Winnow to Context-Sensitive Spelling Correction
Andrew R. Golding, Dan Roth
Multiplicative weight-updating algorithms such as Winnow have been studied extensively in the COLT literature, but only recently have people started to use them in applications. In…
Building Low-Resource NER Models Using Non-Speaker Annotation
Tatiana Tsygankova, Francesca Marini, Stephen Mayhew +1
In low-resource natural language processing (NLP), the key problems are a lack of target language training data, and a lack of native speakers to create it. Cross-lingual methods h…
ExpertQA: Expert-Curated Questions and Attributed Answers
Chaitanya Malaviya, Subin Lee, Sihao Chen +3
As language models are adopted by a more sophisticated and diverse set of users, the importance of guaranteeing that they provide factually correct information supported by verifia…
Comparing Biases and the Impact of Multilingual Training across Multiple Languages
Sharon Levy, Neha Anna John, Ling Liu +6
Studies in bias and fairness in natural language processing have primarily examined social biases within a single language and/or across few attributes (e.g. gender, race). However…
ROCK: Causal Inference Principles for Reasoning about Commonsense Causality
Jiayao Zhang, Hongming Zhang, Weijie J. Su +1
Commonsense causality reasoning (CCR) aims at identifying plausible causes and effects in natural language descriptions that are deemed reasonable by an average person. Although be…
On the Calibration of Multilingual Question Answering LLMs
Yahan Yang, Soham Dan, Dan Roth +1
Multilingual pre-trained Large Language Models (LLMs) are incredibly effective at Question Answering (QA), a core task in Natural Language Understanding, achieving high accuracies…
Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection
Sihao Chen, Fan Zhang, Kazoo Sone +1
Despite significant progress in neural abstractive summarization, recent studies have shown that the current models are prone to generating summaries that are unfaithful to the ori…
DiffuMask: Diffusion Language Model for Token-level Prompt Pruning
Caleb Zheng, Jyotika Singh, Fang Tu +6
In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may co…
LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
Atharv Kulkarni, Kushagra Dixit, Vivek Srikumar +2
Temporal tabular question answering presents a significant challenge for Large Language Models (LLMs), requiring robust reasoning over structured data, which is a task where tradit…
Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering
Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar +2
This work explores the zero-shot capabilities of foundation models in Visual Question Answering (VQA) tasks. We propose an adaptive multi-agent system, named Multi-Agent VQA, to ov…
A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods
Daniel Deutsch, Rotem Dror, Dan Roth
The quality of a summarization evaluation metric is quantified by calculating the correlation between its scores and human annotations across a large number of summaries. Currently…
Temporal Common Sense Acquisition with Minimal Supervision
Ben Zhou, Qiang Ning, Daniel Khashabi +1
Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such informati…
Mapping to Declarative Knowledge for Word Problem Solving
Subhro Roy, Dan Roth
Math word problems form a natural abstraction to a range of quantitative reasoning problems, such as understanding financial news, sports results, and casualties of war. Solving su…
ner and pos when nothing is capitalized
Stephen Mayhew, Tatiana Tsygankova, Dan Roth
For those languages which use it, capitalization is an important signal for the fundamental NLP tasks of Named Entity Recognition (NER) and Part of Speech (POS) tagging. In fact, i…
Two Discourse Driven Language Models for Semantics
Haoruo Peng, Dan Roth
Natural language understanding often requires deep semantic knowledge. Expanding on previous proposals, we suggest that some important aspects of semantic knowledge can be modeled…
Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence
Yangqiu Song, Stephen Mayhew, Dan Roth
This paper presents an approach to classify documents in any language into an English topical label space, without any text categorization training data. The approach, Cross-Lingua…
Benchmarking Answer Verification Methods for Question Answering-Based Summarization Evaluation Metrics
Daniel Deutsch, Dan Roth
Question answering-based summarization evaluation metrics must automatically determine whether the QA model's prediction is correct or not, a task known as answer verification. In…
Question Answering via Integer Programming over Semi-Structured Knowledge
Daniel Khashabi, Tushar Khot, Ashish Sabharwal +3
Answering science questions posed in natural language is an important AI challenge. Answering such questions often requires non-trivial inference and knowledge that goes beyond fac…
On the Possibilities and Limitations of Multi-hop Reasoning Under Linguistic Imperfections
Daniel Khashabi, Erfan Sadeqi Azer, Tushar Khot +2
Systems for language understanding have become remarkably strong at overcoming linguistic imperfections in tasks involving phrase matching or simple reasoning. Yet, their accuracy…
End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions
Wenpeng Yin, Hinrich Schütze, Dan Roth
This work deals with SciTail, a natural entailment challenge derived from a multi-choice question answering problem. The premises and hypotheses in SciTail were generated with no a…
Visual Pivoting for (Unsupervised) Entity Alignment
Fangyu Liu, Muhao Chen, Dan Roth +1
This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs). Images are natural components of many existing KGs. By combi…
TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions
Qiang Ning, Hao Wu, Rujun Han +3
A critical part of reading is being able to understand the temporal relationships between events described in a passage of text, even when those relationships are not explicitly st…
From Spatial Relations to Spatial Configurations
Soham Dan, Parisa Kordjamshidi, Julia Bonn +4
Spatial Reasoning from language is essential for natural language understanding. Supporting it requires a representation scheme that can capture spatial phenomena encountered in la…
Learning Contextual Causality from Time-consecutive Images
Hongming Zhang, Yintong Huo, Xinran Zhao +2
Causality knowledge is crucial for many artificial intelligence systems. Conventional textual-based causality knowledge acquisition methods typically require laborious and expensiv…
SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks
Mohammadtaher Safarzadeh, Hitesh Laxmichand Patel, Afshin Orojlooyjadid +2
Large language models (LLMs) have achieved strong performance on natural language to SQL (NL2SQL) benchmarks, yet their reported accuracy may be inflated by contamination from benc…
SAKE: Structured Agentic Knowledge Extrapolation for Complex LLM Reasoning via Reinforcement Learning
Jiashu He, Jinxuan Fan, Bowen Jiang +3
Knowledge extrapolation is the process of inferring novel information by combining and extending existing knowledge that is explicitly available. It is essential for solving comple…
H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables
Nikhil Abhyankar, Vivek Gupta, Dan Roth +1
Tabular reasoning involves interpreting natural language queries about tabular data, which presents a unique challenge of combining language understanding with structured data anal…
Understanding Spatial Relations through Multiple Modalities
Soham Dan, Hangfeng He, Dan Roth
Recognizing spatial relations and reasoning about them is essential in multiple applications including navigation, direction giving and human-computer interaction in general. Spati…
Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Xingyu Fu, Sheng Zhang, Gukyeong Kwon +10
The open-ended Visual Question Answering (VQA) task requires AI models to jointly reason over visual and natural language inputs using world knowledge. Recently, pre-trained Langua…
On Improving Neurosymbolic Learning by Exploiting the Representation Space
Aaditya Naik, Efthymia Tsamoura, Shibo Jin +2
We study the problem of learning neural classifiers in a neurosymbolic setting where the hidden gold labels of input instances must satisfy a logical formula. Learning in this sett…
Knowledge-Aware Reasoning over Multimodal Semi-structured Tables
Suyash Vardhan Mathur, Jainit Sushil Bafna, Kunal Kartik +5
Existing datasets for tabular question answering typically focus exclusively on text within cells. However, real-world data is inherently multimodal, often blending images such as…
Conceptual and Unbiased Reasoning in Language Models
Ben Zhou, Hongming Zhang, Sihao Chen +5
Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition. However, limited study has been done on large lang…
GLUECons: A Generic Benchmark for Learning Under Constraints
Hossein Rajaby Faghihi, Aliakbar Nafar, Chen Zheng +7
Recent research has shown that integrating domain knowledge into deep learning architectures is effective -- it helps reduce the amount of required data, improves the accuracy of t…
Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction
Haoyu Wang, Hongming Zhang, Yuqian Deng +3
In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives. The first perspective is to extract genuinely based on contextual description…
MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents
Tomer Wolfson, Harsh Trivedi, Mor Geva +5
Automated agents, powered by Large language models (LLMs), are emerging as the go-to tool for querying information. However, evaluation benchmarks for LLM agents rarely feature nat…
Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary
Daniel Deutsch, Tania Bedrax-Weiss, Dan Roth
A desirable property of a reference-based evaluation metric that measures the content quality of a summary is that it should estimate how much information that summary has in commo…
Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval
Peter Baile Chen, Yi Zhang, Dan Roth
Retrieving relevant tables containing the necessary information to accurately answer a given question over tables is critical to open-domain question-answering (QA) systems. Previo…
Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty
Yu Feng, Phu Mon Htut, Zheng Qi +7
Quantifying uncertainty in black-box LLMs is vital for reliable responses and scalable oversight. Existing methods, which gauge a model's uncertainty through evaluating self-consis…
Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
Dhruv Madhwal, Lyuxin David Zhang, Dan Roth +2
Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typic…
Named Person Coreference in English News
Oshin Agarwal, Sanjay Subramanian, Ani Nenkova +1
People are often entities of interest in tasks such as search and information extraction. In these tasks, the goal is to find as much information as possible about people specified…
SacreROUGE: An Open-Source Library for Using and Developing Summarization Evaluation Metrics
Daniel Deutsch, Dan Roth
We present SacreROUGE, an open-source library for using and developing summarization evaluation metrics. SacreROUGE removes many obstacles that researchers face when using or devel…
Exploiting Partially Annotated Data for Temporal Relation Extraction
Qiang Ning, Zhongzhi Yu, Chuchu Fan +1
Annotating temporal relations (TempRel) between events described in natural language is known to be labor intensive, partly because the total number of TempRels is quadratic in the…
"I'd rather just go to bed": Understanding Indirect Answers
Annie Louis, Dan Roth, Filip Radlinski
We revisit a pragmatic inference problem in dialog: understanding indirect responses to questions. Humans can interpret 'I'm starving.' in response to 'Hungry?', even without direc…
Taxonomy Expansion for Named Entity Recognition
Karthikeyan K, Yogarshi Vyas, Jie Ma +7
Training a Named Entity Recognition (NER) model often involves fixing a taxonomy of entity types. However, requirements evolve and we might need the NER model to recognize addition…
Question Answering as Global Reasoning over Semantic Abstractions
Daniel Khashabi, Tushar Khot, Ashish Sabharwal +1
We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning…
PAR-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
Xingyu Li, Rongguang Wang, Yuying Wang +5
Large language models (LLMs) remain brittle on multi-hop question answering (MHQA), where answering requires combining evidence across documents through retrieval and reasoning. It…
AI+HW 2035: Shaping the Next Decade
Deming Chen, Jason Cong, Azalia Mirhoseini +27
Artificial intelligence (AI) and hardware (HW) are advancing at unprecedented rates, yet their trajectories have become inseparably intertwined. The global research community lacks…
Evaluating NL2SQL via SQL2NL
Mohammadtaher Safarzadeh, Afshin Oroojlooyjadid, Dan Roth
Robust evaluation in the presence of linguistic variation is key to understanding the generalization capabilities of Natural Language to SQL (NL2SQL) models, yet existing benchmark…
Building Interpretable and Reliable Open Information Retriever for New Domains Overnight
Xiaodong Yu, Ben Zhou, Dan Roth
Information retrieval (IR) or knowledge retrieval, is a critical component for many down-stream tasks such as open-domain question answering (QA). It is also very challenging, as i…
Analogous Process Structure Induction for Sub-event Sequence Prediction
Hongming Zhang, Muhao Chen, Haoyu Wang +2
Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence…
Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar +3
Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction settings, where attackers strategically…
Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims
Sihao Chen, Daniel Khashabi, Wenpeng Yin +2
One key consequence of the information revolution is a significant increase and a contamination of our information supply. The practice of fact checking won't suffice to eliminate…
A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners
Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao +5
This study introduces a hypothesis-testing framework to assess whether large language models (LLMs) possess genuine reasoning abilities or primarily depend on token bias. We go bey…
No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning
Abhishek Rajgaria, Kushagra Dixit, Mayank Vyas +3
Temporal Table Reasoning is a critical challenge for Large Language Models (LLMs), requiring effective reasoning to extract relevant insights. Despite existence of multiple prompti…
CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm
Hongming Zhang, Yintong Huo, Yanai Elazar +3
Recently, the community has achieved substantial progress on many commonsense reasoning benchmarks. However, it is still unclear what is learned from the training process: the know…
On Learning Latent Models with Multi-Instance Weak Supervision
Kaifu Wang, Efthymia Tsamoura, Dan Roth
We consider a weakly supervised learning scenario where the supervision signal is generated by a transition function of labels associated with multiple input instances. We for…
Conversation Style Transfer using Few-Shot Learning
Shamik Roy, Raphael Shu, Nikolaos Pappas +4
Conventional text style transfer approaches focus on sentence-level style transfer without considering contextual information, and the style is described with attributes (e.g., for…
Improving Generalization in Coreference Resolution via Adversarial Training
Sanjay Subramanian, Dan Roth
In order for coreference resolution systems to be useful in practice, they must be able to generalize to new text. In this work, we demonstrate that the performance of the state-of…
CONCUR: A Framework for Continual Constrained and Unconstrained Routing
Peter Baile Chen, Weiyue Li, Dan Roth +3
AI tasks differ in complexity and are best addressed with different computation strategies (e.g., combinations of models and decoding methods). Hence, an effective routing system t…
JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
Sandip Ghoshal, Anshul Mittal, Jyotika Singh +9
Large language model (LLM) agents augmented with external tools often struggle as number of tools grow large and become domain-specific. In such settings, ambiguous tool descriptio…
World Knowledge as Indirect Supervision for Document Clustering
Chenguang Wang, Yangqiu Song, Dan Roth +2
One of the key obstacles in making learning protocols realistic in applications is the need to supervise them, a costly process that often requires hiring domain experts. We consid…
Large Language Models as Sous Chefs: Revising Recipes with GPT-3
Alyssa Hwang, Bryan Li, Zhaoyi Hou +1
With their remarkably improved text generation and prompting capabilities, large language models can adapt existing written information into forms that are easier to use and unders…
FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation
Bangzheng Li, Ben Zhou, Xingyu Fu +3
Language models have shown impressive in-context-learning capabilities, which allow them to benefit from input prompts and perform better on downstream end tasks. Existing works in…
Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards
Xin Zhang, Xingyu Li, Rongguang Wang +4
Accurate chart comprehension represents a critical challenge in advancing multimodal learning systems, as extensive information is compressed into structured visual representations…
Reasoning is about giving reasons
Krunal Shah, Dan Roth
Convincing someone of the truth value of a premise requires understanding and articulating the core logical structure of the argument which proves or disproves the premise. Underst…
PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
Bowen Jiang, Yuan Yuan, Maohao Shen +13
Personalization is one of the next milestones in advancing AI capability and alignment. We introduce PersonaMem-v2, the state-of-the-art dataset for LLM personalization that simula…
Neural Module Networks for Reasoning over Text
Nitish Gupta, Kevin Lin, Dan Roth +2
Answering compositional questions that require multiple steps of reasoning against text is challenging, especially when they involve discrete, symbolic operations. Neural module ne…
A Learning Approach to Shallow Parsing
Marcia Muñoz, Vasin Punyakanok, Dan Roth +1
A SNoW based learning approach to shallow parsing tasks is presented and studied experimentally. The approach learns to identify syntactic patterns by combining simple predictors t…
On Regularization and Inference with Label Constraints
Kaifu Wang, Hangfeng He, Tin D. Nguyen +2
Prior knowledge and symbolic rules in machine learning are often expressed in the form of label constraints, especially in structured prediction problems. In this work, we compare…
The Use of Classifiers in Sequential Inference
Vasin Punyakanok, Dan Roth
We study the problem of combining the outcomes of several different classifiers in a way that provides a coherent inference that satisfies some constraints. In particular, we devel…
Coreference Reasoning in Machine Reading Comprehension
Mingzhu Wu, Nafise Sadat Moosavi, Dan Roth +1
Coreference resolution is essential for natural language understanding and has been long studied in NLP. In recent years, as the format of Question Answering (QA) became a standard…
LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding
Zhivar Sourati, Zheng Wang, Marianne Menglin Liu +8
Question answering over visually rich documents (VRDs) requires reasoning not only over isolated content but also over documents' structural organization and cross-page dependencie…