{"total":53,"rows":[{"id":"2406.08446","title":"OLMES: A Standard for Language Model Evaluations","created":"2024-06-12","cited_by_count":106,"area":null},{"id":"2502.07068","title":"Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations","created":"2025-02-10","cited_by_count":53,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2407.03129","title":"Social Bias Evaluation for Large Language Models Requires Prompt Variations","created":"2024-07-03","cited_by_count":40,"area":null},{"id":"2412.03205","title":"U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs","created":"2024-12-04","cited_by_count":24,"area":null},{"id":"2407.12344","title":"The Better Angels of Machine Personality: How Personality Relates to LLM Safety","created":"2024-07-17","cited_by_count":21,"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":"2503.06987","title":"Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluations","created":"2025-03-10","cited_by_count":16,"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":"2409.00113","title":"Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options","created":"2024-08-27","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":"2508.09853","title":"STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2601.02316","title":"DatBench: Discriminative, Faithful, and Efficient VLM Evaluations","created":"2026-01-05","cited_by_count":10,"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":"2408.12263","title":"Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates","created":"2024-08-22","cited_by_count":7,"area":null},{"id":"2503.13508","title":"It is Too Many Options: Pitfalls of Multiple-Choice Questions in Generative AI and Medical Education","created":"2025-03-13","cited_by_count":7,"area":null},{"id":"2504.12314","title":"How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2505.15323","title":"Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling","created":"2025-05-21","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":"2407.05327","title":"Can Model Uncertainty Function as a Proxy for Multiple-Choice Question Item Difficulty?","created":"2024-07-07","cited_by_count":5,"area":null},{"id":"2407.11000","title":"Autonomous Prompt Engineering in Large Language Models","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2510.04120","title":"Probing Semantic Alignment, Lexical Invariance, and Syntactic Influence in LLM Metaphor Processing","created":"2025-10-05","cited_by_count":5,"area":null},{"id":"2512.07404","title":"On LLMs' Internal Representation of Code Correctness","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2502.12459","title":"Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2409.15380","title":"Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2508.05429","title":"MyCulture: Exploring Malaysia's Diverse Culture under Low-Resource Language Constraints","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2508.15239","title":"WangchanThaiInstruct: An instruction-following Dataset for Culture-Aware, Multitask, and Multi-domain Evaluation in Thai","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2509.09705","title":"The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2510.24328","title":"Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2502.18798","title":"Choices Speak Louder than Questions","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2507.00999","title":"La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2510.02742","title":"IndiCASA: A Dataset and Bias Evaluation Framework in LLMs Using Contrastive Embedding Similarity in the Indian Context","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2606.11643","title":"Improving Cross-Format Robustness in Language Models with Multi-Format Training","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2502.01243","title":"OphthBench: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Ophthalmology","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2506.11007","title":"Impact of Comments on LLM Comprehension of Legacy Code","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2510.25577","title":"Lost in Phonation: Voice Quality Variation as an Evaluation Dimension for Speech Foundation Models","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2511.21860","title":"Improving Score Reliability of Multiple Choice Benchmarks with Consistency Evaluation and Altered Answer Choices","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.03553","title":"Evaluating LLMs for Police Decision-Making: A Framework Based on Police Action Scenarios","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.18901","title":"Self-Aware Knowledge Probing: Evaluating Language Models' Relational Knowledge through Confidence Calibration","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2602.09346","title":"Digital Linguistic Bias in Spanish: Evidence from Lexical Variation in LLMs","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2605.01846","title":"Do Large Language Models Plan Answer Positions? Position Bias in Multiple-Choice Question Generation","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2607.22554","title":"Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2505.15628","title":"SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2507.15349","title":"Scaling Decentralized Learning with FLock","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2510.00436","title":"Automated Evaluation can Distinguish the Good and Bad AI Responses to Patient Questions about Hospitalization","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2601.11567","title":"Measuring Stability Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric Endocrinology","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2606.16127","title":"AuAu: A Benchmark for Auditing Authoritarian Alignment in Large Language Models","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.23442","title":"Do LLM Debates Repeat Arguments Differently Across Languages?","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.18336","title":"Measuring the Partial-Credit Gap: A Strict Benchmark on Vietnam's 2025 Convex Marking Scheme","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.18726","title":"Execution-grounded evaluation reveals hidden failures in language-model calculations for environmental science","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.21409","title":"Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal Standards?","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.28879","title":"Broadening Uncertainty Estimation for Audio Question Answering Across Methods, Formats, and Inputs","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.02886","title":"Misinformation Without Triggers: From Factual Answers to Downstream Decisions","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}