{"total":19,"rows":[{"id":"2406.08446","title":"OLMES: A Standard for Language Model Evaluations","created":"2024-06-12","cited_by_count":106,"area":null},{"id":"2405.00492","title":"Is Temperature the Creativity Parameter of Large Language Models?","created":"2024-05-01","cited_by_count":93,"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":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35,"area":null},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"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":"2412.07646","title":"Searching for Structure: Investigating Emergent Communication with Large Language Models","created":"2024-12-10","cited_by_count":10,"area":null},{"id":"2503.04395","title":"Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication","created":"2025-03-06","cited_by_count":10,"area":null},{"id":"2403.12675","title":"Pragmatic Competence Evaluation of Large Language Models for the Korean Language","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2511.07659","title":"Revisiting NLI: Towards Cost-Effective and Human-Aligned Metrics for Evaluating LLMs in Question Answering","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2408.07904","title":"Assessing Language Models' Worldview for Fiction Generation","created":"2024-08-15","cited_by_count":3,"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":"2409.18446","title":"Exploring Language Model Generalization in Low-Resource Extractive QA","created":"2024-09-27","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":"2602.16811","title":"Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2410.02343","title":"Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2505.23477","title":"Evaluating the performance and fragility of large language models on the self-assessment for neurological surgeons","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2506.09408","title":"Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models","created":"2025-06-11","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}],"next_cursor":null}