{"total":181,"rows":[{"id":"2309.03882","title":"Large Language Models Are Not Robust Multiple Choice Selectors","created":"2023-09-07","cited_by_count":486,"area":null},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2311.16452","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","created":"2023-11-28","cited_by_count":329,"area":null},{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302,"area":null},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205,"area":null},{"id":"2311.04076","title":"Do LLMs exhibit human-like response biases? A case study in survey design","created":"2023-11-07","cited_by_count":180,"area":null},{"id":"2405.07467","title":"MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation","created":"2024-05-13","cited_by_count":105,"area":null},{"id":"2406.07545","title":"Open-LLM-Leaderboard: From Multi-choice to Open-style Questions for LLMs Evaluation, Benchmark, and Arena","created":"2024-06-11","cited_by_count":76,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","created":"2024-02-19","cited_by_count":71,"area":null},{"id":"2403.17752","title":"Can multiple-choice questions really be useful in detecting the abilities of LLMs?","created":"2024-03-26","cited_by_count":69,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2407.06576","title":"Virtual Personas for Language Models via an Anthology of Backstories","created":"2024-07-09","cited_by_count":51,"area":null},{"id":"2404.03602","title":"Evaluating LLMs at Detecting Errors in LLM Responses","created":"2024-04-04","cited_by_count":50,"area":null},{"id":"2409.02076","title":"LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs","created":"2024-09-03","cited_by_count":47,"area":null},{"id":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41,"area":null},{"id":"2309.08163","title":"Self-Assessment Tests are Unreliable Measures of LLM Personality","created":"2023-09-15","cited_by_count":39,"area":null},{"id":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35,"area":null},{"id":"2410.15393","title":"CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2406.15981","title":"Serial Position Effects of Large Language Models","created":"2024-06-23","cited_by_count":30,"area":null},{"id":"2312.11444","title":"An In-depth Look at Gemini's Language Abilities","created":"2023-12-18","cited_by_count":28,"area":null},{"id":"2410.14582","title":"Do LLMs estimate uncertainty well in instruction-following?","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2502.08045","title":"Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs","created":"2025-02-12","cited_by_count":26,"area":null},{"id":"2401.07955","title":"A Study on Large Language Models' Limitations in Multiple-Choice Question Answering","created":"2024-01-15","cited_by_count":22,"area":null},{"id":"2310.04445","title":"LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model","created":"2023-10-02","cited_by_count":21,"area":null},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2406.03009","title":"Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models","created":"2024-06-05","cited_by_count":20,"area":null},{"id":"2412.00323","title":"Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments","created":"2024-11-30","cited_by_count":20,"area":null},{"id":"2502.06666","title":"Automatic Evaluation of Healthcare LLMs Beyond Question-Answering","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2402.13887","title":"Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models","created":"2024-02-21","cited_by_count":19,"area":null},{"id":"2410.08851","title":"Measuring the Inconsistency of Large Language Models in Preferential Ranking","created":"2024-10-11","cited_by_count":19,"area":null},{"id":"2502.04134","title":"The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs","created":"2025-02-06","cited_by_count":19,"area":null},{"id":"2406.19999","title":"The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models","created":"2024-06-28","cited_by_count":18,"area":null},{"id":"2510.11408","title":"Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification","created":"2025-10-13","cited_by_count":18,"area":null},{"id":"2510.11822","title":"Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2406.01026","title":"Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors","created":"2024-06-03","cited_by_count":15,"area":null},{"id":"2406.03631","title":"Discovering Bias in Latent Space: An Unsupervised Debiasing Approach","created":"2024-06-05","cited_by_count":15,"area":null},{"id":"2410.17632","title":"LMLPA: Language Model Linguistic Personality Assessment","created":"2024-10-23","cited_by_count":15,"area":null},{"id":"2411.05049","title":"ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding","created":"2024-11-07","cited_by_count":15,"area":null},{"id":"2312.01082","title":"A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness","created":"2023-12-02","cited_by_count":14,"area":null},{"id":"2405.10025","title":"Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models","created":"2024-05-16","cited_by_count":14,"area":null},{"id":"2405.19740","title":"PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations","created":"2024-05-30","cited_by_count":13,"area":null},{"id":"2407.01992","title":"Is Your Large Language Model Knowledgeable or a Choices-Only Cheater?","created":"2024-07-02","cited_by_count":12,"area":null},{"id":"2409.18857","title":"Mitigating Selection Bias with Node Pruning and Auxiliary Options","created":"2024-09-27","cited_by_count":12,"area":null},{"id":"2404.17120","title":"Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs","created":"2024-04-26","cited_by_count":11,"area":null},{"id":"2410.13204","title":"Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations","created":"2024-10-17","cited_by_count":11,"area":null},{"id":"2410.14248","title":"Addressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models","created":"2024-10-18","cited_by_count":11,"area":null},{"id":"2502.18125","title":"HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge","created":"2025-02-25","cited_by_count":11,"area":null},{"id":"2510.00307","title":"BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models","created":"2025-09-30","cited_by_count":11,"area":null},{"id":"2311.00217","title":"Can Large Language Models Capture Public Opinion about Global Warming? An Empirical Assessment of Algorithmic Fidelity and Bias","created":"2023-11-01","cited_by_count":9,"area":null},{"id":"2406.16135","title":"Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models","created":"2024-06-23","cited_by_count":9,"area":null},{"id":"2506.00643","title":"SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questions","created":"2025-05-31","cited_by_count":9,"area":null},{"id":"2510.04398","title":"SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations","created":"2025-10-05","cited_by_count":9,"area":null},{"id":"2510.11905","title":"LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2603.20422","title":"PEARL: Personalized Streaming Video Understanding Model","created":"2026-03-20","cited_by_count":9,"area":null},{"id":"2609.25845","title":"Visual Jev: Accurate and Efficient Decisions from Shared Visual Context","created":"2026-09-22","cited_by_count":9,"area":null},{"id":"2405.19323","title":"Are Large Language Models Chameleons? An Attempt to Simulate Social Surveys","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2411.02018","title":"Shortcut Learning in In-Context Learning: A Survey","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2503.07003","title":"Large Language Models Often Say One Thing and Do Another","created":"2025-03-10","cited_by_count":8,"area":null},{"id":"2509.19364","title":"The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behavior","created":"2025-09-18","cited_by_count":8,"area":null},{"id":"2605.18890","title":"Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits","created":"2026-05-17","cited_by_count":8,"area":null},{"id":"2502.12477","title":"Savaal: Scalable Concept-Driven Question Generation to Enhance Human Learning","created":"2025-02-18","cited_by_count":7,"area":null},{"id":"2503.23688","title":"Mapping Geopolitical Bias in 11 Large Language Models: A Bilingual, Dual-Framing Analysis of U.S.-China Tensions","created":"2025-03-31","cited_by_count":7,"area":null},{"id":"2504.13475","title":"LLM Sensitivity Evaluation Framework for Clinical Diagnosis","created":"2025-04-18","cited_by_count":7,"area":null},{"id":"2310.02953","title":"JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning","created":"2023-10-04","cited_by_count":6,"area":null},{"id":"2310.10083","title":"JMedLoRA:Medical Domain Adaptation on Japanese Large Language Models using Instruction-tuning","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2406.06581","title":"Order-Independence Without Fine Tuning","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2505.18545","title":"B-score: Detecting biases in large language models using response history","created":"2025-05-24","cited_by_count":6,"area":null},{"id":"2509.23782","title":"Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","cited_by_count":6,"area":null},{"id":"2504.12562","title":"ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2506.14092","title":"Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2506.18710","title":"Benchmarking the Pedagogical Knowledge of Large Language Models","created":"2025-06-23","cited_by_count":5,"area":null},{"id":"2509.02949","title":"ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2510.00628","title":"Hearing the Order: Investigating Position Bias in Large Audio-Language Models","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2601.22548","title":"Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2602.06181","title":"Investigating Social Bias Changes in Quantized Language Models","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2402.00956","title":"Exploring Spatial Schema Intuitions in Large Language and Vision Models","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2408.07465","title":"Large Language Models Prompting With Episodic Memory","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2502.06087","title":"ConMeC: A Dataset for Metonymy Resolution with Common Nouns","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2510.25356","title":"Prompting from the bench: Large-scale pretraining is not sufficient to prepare LLMs for ordinary meaning analysis","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2609.30243","title":"JevOut: Natural Context Can Flip Decision Models","created":"2026-09-24","cited_by_count":4,"area":null},{"id":"2610.02076","title":"LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them","created":"2026-10-01","cited_by_count":4,"area":null},{"id":"2406.07685","title":"Test-Time Fairness and Robustness in Large Language Models","created":"2024-06-11","cited_by_count":3,"area":null},{"id":"2406.14882","title":"70B-parameter large language models in Japanese medical question-answering","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2502.08662","title":"RoToR: Towards More Reliable Responses for Order-Invariant Inputs","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2505.12938","title":"Leveraging LLM Inconsistency to Boost Pass@k Performance","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2602.17445","title":"ABCD: All Biases Come Disguised","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2603.23114","title":"On the Context Sensitivity of LLM Moral Judgment","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2609.32160","title":"Typed Decision Models: An Early Evidence Audit and Evaluation Checklist","created":"2026-09-26","cited_by_count":3,"area":null},{"id":"2310.07225","title":"Do Large Language Models have Shared Weaknesses in Medical Question Answering?","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2405.18028","title":"Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2502.18798","title":"Choices Speak Louder than Questions","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2504.08300","title":"Large Language Models Could Be Rote Learners","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2507.18182","title":"SCOPE: Stochastic and Counterbiased Option Placement for Evaluating Large Language Models","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2509.24125","title":"The Impossibility of Inverse Permutation Learning in Transformer Models","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2604.05051","title":"This Treatment Works, Right? Evaluating LLM Sensitivity to Patient Question Framing in Medical QA","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2605.13045","title":"Large Language Models Lack Temporal Awareness of Medical Knowledge","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.15393","title":"LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling","created":"2026-05-14","cited_by_count":2,"area":null}],"next_cursor":"100"}