{"total":72,"rows":[{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318,"area":null},{"id":"2305.10037","title":"Can Language Models Solve Graph Problems in Natural Language?","created":"2023-05-17","cited_by_count":252,"area":"lr"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2505.23840","title":"Measuring Sycophancy of Language Models in Multi-turn Dialogues","created":"2025-05-28","cited_by_count":104,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2212.10003","title":"(QA)$^2$: Question Answering with Questionable Assumptions","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2307.02394","title":"Won't Get Fooled Again: Answering Questions with False Premises","created":"2023-07-05","cited_by_count":48,"area":null},{"id":"2306.07934","title":"BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information","created":"2023-06-13","cited_by_count":44,"area":"lr"},{"id":"2311.09731","title":"Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge","created":"2023-11-16","cited_by_count":32,"area":null},{"id":"2305.14010","title":"IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2305.13733","title":"Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting","created":"2023-05-23","cited_by_count":21,"area":null},{"id":"2503.09598","title":"How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation","created":"2025-03-12","cited_by_count":18,"area":null},{"id":"2410.04241","title":"Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations","created":"2024-10-05","cited_by_count":15,"area":null},{"id":"2504.06438","title":"Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning","created":"2025-04-08","cited_by_count":15,"area":"lr"},{"id":"2504.11373","title":"Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions","created":"2025-04-15","cited_by_count":15,"area":null},{"id":"2311.09542","title":"Pregnant Questions: The Importance of Pragmatic Awareness in Maternal Health Question Answering","created":"2023-11-16","cited_by_count":14,"area":null},{"id":"2410.15512","title":"Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?","created":"2024-10-20","cited_by_count":13,"area":null},{"id":"2509.22449","title":"Detecting (Un)answerability in Large Language Models with Linear Directions","created":"2025-09-26","cited_by_count":13,"area":null},{"id":"2312.08800","title":"Evaluating Large Language Models for Health-related Queries with Presuppositions","created":"2023-12-14","cited_by_count":12,"area":null},{"id":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","cited_by_count":12,"area":null},{"id":"2503.21817","title":"Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping","created":"2025-03-26","cited_by_count":12,"area":"mllm"},{"id":"2505.22354","title":"LLMs Struggle to Reject False Presuppositions when Misinformation Stakes are High","created":"2025-05-28","cited_by_count":12,"area":null},{"id":"2506.08952","title":"Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2402.19103","title":"Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models","created":"2024-02-29","cited_by_count":9,"area":null},{"id":"2407.05868","title":"KG-FPQ: Evaluating Factuality Hallucination in LLMs with Knowledge Graph-based False Premise Questions","created":"2024-07-08","cited_by_count":9,"area":null},{"id":"2506.00264","title":"MultiHoax: A Dataset of Multi-hop False-Premise Questions","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2505.23715","title":"Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2406.16342","title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2407.17469","title":"I Could've Asked That: Reformulating Unanswerable Questions","created":"2024-07-24","cited_by_count":6,"area":null},{"id":"2410.06524","title":"Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA","created":"2024-10-09","cited_by_count":6,"area":"lr"},{"id":"2411.17993","title":"DRS: Deep Question Reformulation With Structured Output","created":"2024-11-27","cited_by_count":6,"area":null},{"id":"2305.14237","title":"HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision","created":"2023-05-23","cited_by_count":5,"area":"lr"},{"id":"2403.12145","title":"Syn-QA2: Evaluating False Assumptions in Long-tail Questions with Synthetic QA Datasets","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2502.19684","title":"GRACE: A Granular Benchmark for Evaluating Model Calibration against Human Calibration","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2607.08456","title":"Two Axes of LLM Abstention: Answer Correctness and Question Answerability","created":"2026-07-09","cited_by_count":5,"area":null},{"id":"2310.16147","title":"PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2412.12300","title":"Unanswerability Evaluation for Retrieval Augmented Generation","created":"2024-12-16","cited_by_count":4,"area":"rag"},{"id":"2405.01588","title":"Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2505.23461","title":"UAQFact: Evaluating Factual Knowledge Utilization of LLMs on Unanswerable Questions","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2609.09090","title":"SPINE: Measuring LLM Sycophancy under Sustained Multi-Turn Pressure","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2410.14567","title":"ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions","created":"2024-10-18","cited_by_count":2,"area":"rag"},{"id":"2505.15576","title":"Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models","created":"2025-05-21","cited_by_count":2,"area":"lr"},{"id":"2511.18749","title":"Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Search","created":"2025-11-24","cited_by_count":2,"area":"lr"},{"id":"2605.13737","title":"Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2401.11185","title":"How the Advent of Ubiquitous Large Language Models both Stymie and Turbocharge Dynamic Adversarial Question Generation","created":"2024-01-20","cited_by_count":1,"area":null},{"id":"2404.16262","title":"Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2406.13232","title":"Towards Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2506.00914","title":"How do Transformer Embeddings Represent Compositions? A Functional Analysis","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2508.03622","title":"Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation Framework","created":"2025-08-05","cited_by_count":1,"area":"lr"},{"id":"2509.00740","title":"Efficient Graph Understanding with LLMs via Structured Context Injection","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2603.00925","title":"The Aftermath of DrawEduMath: Vision Language Models Underperform with Struggling Students and Misdiagnose Errors","created":"2026-03-01","cited_by_count":1,"area":"mllm"},{"id":"2604.21766","title":"AUDITA: A New Dataset to Audit Humans vs. AI Skill at Audio QA","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2607.18232","title":"It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2608.06539","title":"Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performance","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2608.20220","title":"InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2609.06842","title":"XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?","created":"2026-09-06","cited_by_count":1,"area":null},{"id":"2508.15139","title":"Identifying and Answering Questions with False Assumptions: An Interpretable Approach","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2510.13749","title":"Assessing Web Search Credibility and Response Groundedness in Chat Assistants","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2601.09853","title":"MedRedFlag: Investigating how LLMs Redirect Misconceptions in Real-World Health Communication","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.15674","title":"What Patients Really Ask: Exploring the Effect of False Assumptions in Patient Information Seeking","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2604.15140","title":"DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answering","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.06213","title":"Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.06476","title":"Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.05616","title":"What's in a Name? Morphological Shortcuts by LLMs in Pharmacology","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.12884","title":"Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.09551","title":"Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2609.23939","title":"XYEval: Agents say yes to bad advice","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.27603","title":"When Context Misleads: In-context Learning with Jurisdiction in Large Language Models","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.05170","title":"Verification Trap: Understanding Test-Time Selection Failures under False Premises in Code Generation","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.17703","title":"Pushback in a Haystack: Language Models Respond to Factual Errors Ambiguously and Ineffectively","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}