Synergizing Large Language Models and Theory for Human-like Causal Reasoning

arXiv:2505.08750 · cs.CL · Submitted 2025-05-13 · Read on arXiv

cs.CL

Submitted: 2025-05-13

Updated: 2026-10-12

Comments: Accepted to AACL-IJCNLP 2026 (Long Paper)

Code: https://github.com/zhangyx0417/hcr_reasoner

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Causal Reasoning — 4× in this paper · explained in 2 episodes
• Actual Causality — 3× in this paper · explained in 1 episode
• Alignment — 1× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• Causal Evaluation of Language Models
• Do Large Language Models Reason Causally Like Us? Even Better?
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• GPT-4o System Card
• DeepSeek-V3 Technical Report
• Qwen2.5 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering