Artificial Intelligence › Core AI ›

Reasoning

2595 directly classified papers

Papers per year

Papers

Assimilation and Accommodation: Task-Adaptive Hierarchical Abstraction for Solving Web Tasks ACL 2025

Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving ACL 2025

On the Consistency of Commonsense in Large Language Models ACL 2025

ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models ACL 2025

TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues ACL 2025

Confidence Improves Self-Consistency in LLMs ACL 2025

LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs ACL 2025

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation ACL 2025

MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance ACL 2025

CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought ACL 2025

Can Stories Help LLMs Reason? Curating Information Space Through Narrative ACL 2025

Testing Spatial Intuitions of Humans and Large Language and Multimodal Models in Analogies ACL 2025

“The Facts Speak for Themselves”: GPT and Fallacy Classification ACL 2025

Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design ACL 2025

Multi-Agent LLM Debate Unveils the Premise Left Unsaid ACL 2025

Reproducing the Argument Quality Prediction of Project Debater ACL 2025

Multi-Class versus Means-End: Assessing Classification Approaches for Argument Patterns ACL 2025

Tdnguyen at CQs-Gen 2025: Adapt Large Language Models with Multi-Step Reasoning for Critical Questions Generation ACL 2025

DayDreamer at CQs-Gen 2025: Generating Critical Questions through Argument Scheme Completion ACL 2025

Analyzing Interview Questions via Bloom’s Taxonomy to Enhance the Design Thinking Process ACL 2025

Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic ACL 2025

WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization ACL 2025

SANCTUARY: An Efficient Evidence-based Automated Fact Checking System ACL 2025

Graph-of-Thoughts for Fact-Checking with Large Language Models ACL 2025

PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation CVPR 2025