{"total":14,"rows":[{"id":"2412.15204","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","created":"2024-12-19","cited_by_count":379,"area":"lr"},{"id":"2412.17837","title":"Evaluating the Capabilities of Large Language Models for Multi-label Emotion Understanding","created":"2024-12-17","cited_by_count":17,"area":"lr"},{"id":"2409.06173","title":"Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks","created":"2024-09-10","cited_by_count":8,"area":"lr"},{"id":"2503.11655","title":"Explainable Sentiment Analysis with DeepSeek-R1: Performance, Efficiency, and Few-Shot Learning","created":"2025-02-03","cited_by_count":5,"area":"lr"},{"id":"2307.01784","title":"The Inner Sentiments of a Thought","created":"2023-07-04","cited_by_count":4,"area":"lr"},{"id":"2502.19163","title":"TestNUC: Enhancing Test-Time Computing Approaches and Scaling through Neighboring Unlabeled Data Consistency","created":"2025-02-26","cited_by_count":4,"area":"lr"},{"id":"2502.09101","title":"A Survey of LLM Alignment: Instruction Understanding, Intention Reasoning, and Reliable Generation","created":"2025-02-13","cited_by_count":3,"area":"lr"},{"id":"2212.00482","title":"IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selection","created":"2022-12-01","cited_by_count":2,"area":"lr"},{"id":"2602.09442","title":"Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2603.09205","title":"Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2604.07801","title":"TEMPER: Testing Emotional Perturbation in Quantitative Reasoning","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2603.09993","title":"CEI: A Benchmark for Evaluating Pragmatic Reasoning in Language Models","created":"2026-02-14","cited_by_count":0,"area":"lr"},{"id":"2607.27384","title":"Same Facts, Different Diagnosis: Measuring and Mitigating Narrative Anchoring in Clinical Language Models","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.21369","title":"Wazobia Eval: A Benchmark for Nigerian Pidgin Emotion Understanding, Sarcasm Detection, and Cultural Reasoning","created":"2026-06-21","cited_by_count":0,"area":"lr"}],"next_cursor":null}