{"total":99,"rows":[{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006,"area":"agents"},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447,"area":null},{"id":"2305.16739","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","created":"2023-05-26","cited_by_count":288,"area":null},{"id":"2112.08542","title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","created":"2021-12-16","cited_by_count":236,"area":null},{"id":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"area":null},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152,"area":null},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"id":"2203.07190","title":"CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment","created":"2022-03-14","cited_by_count":113,"area":null},{"id":"2312.16337","title":"Task Contamination: Language Models May Not Be Few-Shot Anymore","created":"2023-12-26","cited_by_count":99,"area":null},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85,"area":null},{"id":"2103.12248","title":"Multi-Modal Answer Validation for Knowledge-Based VQA","created":"2021-03-23","cited_by_count":79,"area":null},{"id":"2106.09449","title":"DocNLI: A Large-scale Dataset for Document-level Natural Language Inference","created":"2021-06-17","cited_by_count":75,"area":null},{"id":"2203.12990","title":"Generating Scientific Claims for Zero-Shot Scientific Fact Checking","created":"2022-03-24","cited_by_count":59,"area":null},{"id":"2104.08731","title":"Can NLI Models Verify QA Systems' Predictions?","created":"2021-04-18","cited_by_count":46,"area":null},{"id":"2105.14682","title":"Zero-shot Fact Verification by Claim Generation","created":"2021-05-31","cited_by_count":42,"area":null},{"id":"2211.11875","title":"Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference","created":"2022-11-21","cited_by_count":40,"area":null},{"id":"2210.12217","title":"Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning","created":"2022-10-21","cited_by_count":38,"area":null},{"id":"2204.13074","title":"Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement","created":"2022-04-27","cited_by_count":37,"area":"lr"},{"id":"2402.15179","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","created":"2024-02-23","cited_by_count":37,"area":null},{"id":"2107.02153","title":"FaVIQ: FAct Verification from Information-seeking Questions","created":"2021-07-05","cited_by_count":36,"area":null},{"id":"2205.06009","title":"Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization","created":"2022-05-12","cited_by_count":34,"area":null},{"id":"2311.02216","title":"Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data","created":"2023-11-03","cited_by_count":33,"area":"lr"},{"id":"2304.09138","title":"Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task","created":"2023-04-18","cited_by_count":32,"area":null},{"id":"2305.07614","title":"NevIR: Negation in Neural Information Retrieval","created":"2023-05-12","cited_by_count":29,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2203.14187","title":"Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric Summarization","created":"2022-03-27","cited_by_count":26,"area":null},{"id":"2305.07982","title":"Zero-shot Faithful Factual Error Correction","created":"2023-05-13","cited_by_count":26,"area":null},{"id":"2402.12656","title":"HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts","created":"2024-02-20","cited_by_count":26,"area":"moe"},{"id":"2205.01376","title":"Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning","created":"2022-05-03","cited_by_count":25,"area":null},{"id":"2210.04982","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","created":"2022-10-10","cited_by_count":22,"area":null},{"id":"2407.04118","title":"MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization","created":"2024-07-04","cited_by_count":21,"area":null},{"id":"2105.11776","title":"Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering","created":"2021-05-25","cited_by_count":17,"area":null},{"id":"2107.11879","title":"Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration","created":"2021-07-25","cited_by_count":17,"area":null},{"id":"2212.04408","title":"OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2209.07662","title":"NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning","created":"2022-09-16","cited_by_count":16,"area":"lr"},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2109.02905","title":"Exploiting Reasoning Chains for Multi-hop Science Question Answering","created":"2021-09-07","cited_by_count":15,"area":null},{"id":"2210.06748","title":"Shortcomings of Question Answering Based Factuality Frameworks for Error Localization","created":"2022-10-13","cited_by_count":15,"area":null},{"id":"2305.14250","title":"Language Models with Rationality","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2307.09254","title":"Selective Generation for Controllable Language Models","created":"2023-07-18","cited_by_count":15,"area":null},{"id":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2405.16702","title":"Accurate and Nuanced Open-QA Evaluation Through Textual Entailment","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2402.14798","title":"Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2405.05135","title":"Lessons from the Use of Natural Language Inference (NLI) in Requirements Engineering Tasks","created":"2024-04-24","cited_by_count":12,"area":null},{"id":"2305.13256","title":"TaskWeb: Selecting Better Source Tasks for Multi-task NLP","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2110.07165","title":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2210.12587","title":"Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning","created":"2022-10-23","cited_by_count":9,"area":null},{"id":"2206.04869","title":"Ask to Know More: Generating Counterfactual Explanations for Fake Claims","created":"2022-06-10","cited_by_count":8,"area":null},{"id":"2312.11785","title":"Zero-Shot Fact-Checking with Semantic Triples and Knowledge Graphs","created":"2023-12-19","cited_by_count":8,"area":null},{"id":"2406.12375","title":"GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory","created":"2024-06-18","cited_by_count":8,"area":"moe"},{"id":"2105.03417","title":"Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference","created":"2021-05-07","cited_by_count":7,"area":null},{"id":"2310.16681","title":"BabyStories: Can Reinforcement Learning Teach Baby Language Models to Write Better Stories?","created":"2023-10-25","cited_by_count":7,"area":"alignment"},{"id":"2402.15082","title":"PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning","created":"2024-02-23","cited_by_count":7,"area":"moe"},{"id":"2310.11670","title":"Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2406.03239","title":"Document-level Claim Extraction and Decontextualisation for Fact-Checking","created":"2024-06-05","cited_by_count":6,"area":null},{"id":"2503.18063","title":"Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning","created":"2025-03-23","cited_by_count":6,"area":null},{"id":"2109.05793","title":"Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models","created":"2021-09-13","cited_by_count":5,"area":null},{"id":"2111.07935","title":"Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection","created":"2021-11-15","cited_by_count":5,"area":null},{"id":"2307.01458","title":"CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care","created":"2023-07-04","cited_by_count":5,"area":null},{"id":"2310.16446","title":"Diversity Enhanced Narrative Question Generation for Storybooks","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2212.06971","title":"Find Someone Who: Visual Commonsense Understanding in Human-Centric Grounding","created":"2022-12-14","cited_by_count":4,"area":null},{"id":"2306.09918","title":"No Strong Feelings One Way or Another: Re-operationalizing Neutrality in Natural Language Inference","created":"2023-06-16","cited_by_count":4,"area":"lr"},{"id":"2307.16689","title":"No that's not what I meant: Handling Third Position Repair in Conversational Question Answering","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2312.00471","title":"A Bayesian approach for prompt optimization in pre-trained language models","created":"2023-12-01","cited_by_count":4,"area":null},{"id":"2312.10171","title":"Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language","created":"2023-12-15","cited_by_count":4,"area":null},{"id":"2410.03429","title":"How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2503.08890","title":"PlainQAFact: Retrieval-augmented Factual Consistency Evaluation Metric for Biomedical Plain Language Summarization","created":"2025-03-11","cited_by_count":4,"area":"rag"},{"id":"2108.01208","title":"User-Initiated Repetition-Based Recovery in Multi-Utterance Dialogue Systems","created":"2021-08-02","cited_by_count":3,"area":null},{"id":"2204.09519","title":"A Survey on Neural Abstractive Summarization Methods and Factual Consistency of Summarization","created":"2022-04-20","cited_by_count":3,"area":null},{"id":"2211.12641","title":"Leveraging Data Recasting to Enhance Tabular Reasoning","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2212.01956","title":"Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation","created":"2022-12-04","cited_by_count":3,"area":null},{"id":"2304.11257","title":"Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers","created":"2023-04-21","cited_by_count":3,"area":null},{"id":"2305.17369","title":"Modularized Zero-shot VQA with Pre-trained Models","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2305.17491","title":"FERMAT: An Alternative to Accuracy for Numerical Reasoning","created":"2023-05-27","cited_by_count":3,"area":"lr"},{"id":"2306.12552","title":"SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning","created":"2023-06-21","cited_by_count":3,"area":"lr"},{"id":"2306.15273","title":"IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning","created":"2023-06-27","cited_by_count":3,"area":"lr"},{"id":"2402.08594","title":"Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2410.13206","title":"BQA: Body Language Question Answering Dataset for Video Large Language Models","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2411.05762","title":"Multi-hop Evidence Pursuit Meets the Web: Team Papelo at FEVER 2024","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2104.08410","title":"Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models","created":"2021-04-17","cited_by_count":2,"area":null},{"id":"2204.06970","title":"Can Visual Dialogue Models Do Scorekeeping? Exploring How Dialogue Representations Incrementally Encode Shared Knowledge","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2310.14126","title":"Ask To The Point: Open-Domain Entity-Centric Question Generation","created":"2023-10-21","cited_by_count":2,"area":null},{"id":"2403.17431","title":"Robust and Scalable Model Editing for Large Language Models","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2105.03791","title":"Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning","created":"2021-05-08","cited_by_count":1,"area":null},{"id":"2210.09179","title":"Zero-Shot Ranking Socio-Political Texts with Transformer Language Models to Reduce Close Reading Time","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2410.12847","title":"ACCEPT: Adaptive Codebook for Composite and Efficient Prompt Tuning","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2502.20399","title":"Momentum Posterior Regularization for Multi-hop Dense Retrieval","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2510.19675","title":"Study of Training Dynamics for Memory-Constrained Fine-Tuning","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2211.05598","title":"Using contradictions improves question answering systems","created":"2022-09-28","cited_by_count":0,"area":null},{"id":"2305.13499","title":"Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefixes","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2312.09932","title":"RDR: the Recap, Deliberate, and Respond Method for Enhanced Language Understanding","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2510.09696","title":"Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.15972","title":"Quantum NLP models on Natural Language Inference","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2510.16716","title":"DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the Edge","created":"2025-10-19","cited_by_count":0,"area":"distill"},{"id":"2510.20979","title":"Memory Constrained Dynamic Subnetwork Update for Transfer Learning","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2510.24295","title":"MERGE: Minimal Expression-Replacement GEneralization Test for Natural Language Inference","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2604.11841","title":"Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2609.01369","title":"How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}