{"total":14,"rows":[{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88,"area":"lr"},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2410.06458","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","created":"2024-10-09","cited_by_count":35,"area":"lr"},{"id":"2309.08591","title":"Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings","created":"2023-09-15","cited_by_count":32,"area":"lr"},{"id":"2503.22395","title":"Negation: A Pink Elephant in the Large Language Models' Room?","created":"2025-03-28","cited_by_count":7,"area":"lr"},{"id":"2310.14868","title":"Assessing Step-by-Step Reasoning against Lexical Negation: A Case Study on Syllogism","created":"2023-10-23","cited_by_count":6,"area":"lr"},{"id":"2402.10543","title":"Strong hallucinations from negation and how to fix them","created":"2024-02-16","cited_by_count":6,"area":"lr"},{"id":"2506.09677","title":"Benchmarking Gaslighting Negation Attacks Against Reasoning Models","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2509.03162","title":"SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala","created":"2025-09-03","cited_by_count":6,"area":"lr"},{"id":"2409.18998","title":"Controlled LLM-based Reasoning for Clinical Trial Retrieval","created":"2024-09-19","cited_by_count":3,"area":"lr"},{"id":"2402.06120","title":"Exploring Group and Symmetry Principles in Large Language Models","created":"2024-02-09","cited_by_count":2,"area":"lr"},{"id":"2508.16697","title":"QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting","created":"2025-08-22","cited_by_count":1,"area":"lr"},{"id":"2602.20332","title":"No One Size Fits All: QueryBandits for Hallucination Mitigation","created":"2026-02-23","cited_by_count":0,"area":"lr"},{"id":"2604.14749","title":"Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement","created":"2026-04-16","cited_by_count":0,"area":"lr"}],"next_cursor":null}