ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis

arXiv:2602.06373 · cs.CL · Submitted 2026-02-06 · Read on arXiv

cs.CL

Submitted: 2026-02-06

Updated: 2026-09-06

Comments: Accepted to Findings of the Association for Computational Linguistics: EMNLP 2026

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

Terminology

• Generalizability — 16× in this paper · explained in 6 episodes
• Verification — 16× in this paper · explained in 2 episodes
• Clarity and Organization — 10× in this paper
• Consistency — 10× in this paper · explained in 3 episodes
• Clustering — 7× in this paper · explained in 2 episodes
• Causal Discovery — 6× in this paper · explained in 2 episodes
• Abstraction — 5× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• Interpretability — 5× in this paper · explained in 15 episodes
• Score Function — 5× in this paper · explained in 4 episodes
• Hallucination — 4× in this paper · explained in 3 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Causal Inference — 3× in this paper · explained in 4 episodes
• Core — 3× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Self-consistency — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Grounding — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Additivity — 1× in this paper · explained in 1 episode
• Adjacency Matrix — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Graph Construction — 1× in this paper · explained in 3 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Randomized Controlled Trial — 1× in this paper
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Uncertainty Quantification — 1× in this paper · explained in 8 episodes

Sources

• Invariant Risk Minimization
• Qwen Technical Report
• Teaching Large Language Models to Self-Debug
• CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
• Measuring Mathematical Problem Solving With the MATH Dataset
• Large Language Models Cannot Self-Correct Reasoning Yet
• Why Language Models Hallucinate
• SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
• LLMs Get Lost In Multi-Turn Conversation
• When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models
• Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
• REFINER: Reasoning Feedback on Intermediate Representations
• GPT-4 Technical Report
• Shepherd: A Critic for Language Model Generation
• Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
• The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning
• Why Does ChatGPT Fall Short in Providing Truthful Answers?

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