Reasoning

Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty EMNLP 2025 Seeing Culture: A Benchmark for Visual Reasoning and Grounding EMNLP 2025 Self-attention-based Graph-of-Thought for Math Problem Solving ACL 2025 Self-Consistency Preference Optimization ICML 2025 Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks ACL 2025 Self-Critique and Refinement for Faithful Natural Language Explanations EMNLP 2025 Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering ACL 2025 Self-Harmonized Chain of Thought NAACL 2025 SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses AAAI 2025 Self-Taught Agentic Long Context Understanding ACL 2025 Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models ACL 2025 Semantic Inversion, Identical Replies: Revisiting Negation Blindness in Large Language Models EMNLP 2025 seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs EMNLP 2025 SGCD: Subtask-Guided Causal-Debiasing Framework for Robust Cross-Utterance Sentiment Quadruple Extraction in Dialogues EMNLP 2025 SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine NAACL 2025 Shifting from Ranking to Set Selection for Retrieval Augmented Generation ACL 2025 Should I Believe in What Medical AI Says? A Chinese Benchmark for Medication Based on Knowledge and Reasoning ACL 2025 Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions ACL 2025 SITE: towards Spatial Intelligence Thorough Evaluation ICCV 2025 SKE-Layout: Spatial Knowledge Enhanced Layout Generation with LLMs CVPR 2025 Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching EMNLP 2025 Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster EMNLP 2025 Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency EMNLP 2025 SMART: Self-Aware Agent for Tool Overuse Mitigation ACL 2025 Snap Out of It: A Dual-Process Approach to Mitigating Overthinking in Language Model Reasoning ACL 2025