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

• URL: http://arxiv.org/abs/2602.06373v1
• Date: Fri, 06 Feb 2026 04:00:57 GMT
• Title: ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis
• Authors: Tianqiang Yan, Sihan Shang, Yuheng Li, Song Qiu, Hao Peng, Wenjian Luo, Jue Xie, Lizhen Qu, Yuan Gao,
• Abstract summary: We introduce textbftextttReBeCA (self-textbftexttReflection textbftextttBehavior explained through textbftextttBehavior), a framework that unveils the interpretable behavioral hierarchy governing the self-reflection outcome.<n>By modeling self-reflection trajectories as causal graphs, ReBeCA isolates genuine determinants of performance.
• Score: 35.12196884025294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While self-reflection can enhance language model reliability, its underlying mechanisms remain opaque, with existing analyses often yielding correlation-based insights that fail to generalize. To address this, we introduce \textbf{\texttt{ReBeCA}} (self-\textbf{\texttt{Re}}flection \textbf{\texttt{Be}}havior explained through \textbf{\texttt{C}}ausal \textbf{\texttt{A}}nalysis), a framework that unveils the interpretable behavioral hierarchy governing the self-reflection outcome. By modeling self-reflection trajectories as causal graphs, ReBeCA isolates genuine determinants of performance through a three-stage Invariant Causal Prediction (ICP) pipeline. We establish three critical findings: (1) \textbf{Behavioral hierarchy:} Semantic behaviors of the model influence final self-reflection results hierarchically: directly or indirectly; (2) \textbf{Causation matters:} Generalizability in self-reflection effects is limited to just a few semantic behaviors; (3) \textbf{More $\mathbf{\neq}$ better:} The confluence of seemingly positive semantic behaviors, even among direct causal factors, can impair the efficacy of self-reflection. ICP-based verification identifies sparse causal parents achieving up to $49.6\%$ structural likelihood gains, stable across tasks where correlation-based patterns fail. Intervention studies on novel datasets confirm these causal relationships hold out-of-distribution ($p = .013, η^2_\mathrm{p} = .071$). ReBeCA thus provides a rigorous methodology for disentangling genuine causal mechanisms from spurious associations in self-reflection dynamics.

Related papers

• Scalable Contrastive Causal Discovery under Unknown Soft Interventions [3.165716101116899]
  We propose a scalable causal discovery model for paired observational and interventional settings with shared underlying causal structure and unknown soft interventions.<n> Experiments on synthetic data demonstrate improved causal structure recovery, generalization to unseen graphs with held-out causal mechanisms, and scalability to larger graphs.
  arXiv  Detail & Related papers  (2026-03-03T18:16:16Z)
• CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching [50.65932158912512]
  We propose a new causal reasoning benchmark, CausalFlip, to encourage the development of new large language models.<n>CaulFlip consists of causal judgment questions built over event triples that could form different confounder, chain, and collider relations.<n>We evaluate LLMs under multiple training paradigms, including answer-only training, explicit Chain-of-Thought supervision, and a proposed internalized causal reasoning approach.
  arXiv  Detail & Related papers  (2026-02-23T18:06:15Z)
• Causality is Key for Interpretability Claims to Generalise [35.833847356014154]
  Interpretability research on large language models (LLMs) has yielded important insights into model behaviour.<n> recurring pitfalls persist: findings that do not generalise, and causal interpretations that outrun the evidence.<n>Pearl's causal hierarchy clarifies what an interpretability study can justify.
  arXiv  Detail & Related papers  (2026-02-18T18:45:04Z)
• Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation [27.571918867764932]
  We formalize the phenomenon through a three-level measurement hierarchy.<n>We analyze semantic suppression, the intuitive mitigation strategy that instructs models to ignore the answer.<n>We propose Structural Skeleton-guided Reasoning (SSR), a two-phase approach that first generates an answer-invariant functional skeleton structure.
  arXiv  Detail & Related papers  (2026-02-16T05:13:06Z)
• Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure [58.89643769707751]
  We study latent chain-of-thought as a manipulable causal process in representation space.<n>We find that latent-step budgets behave less like homogeneous extra depth and more like staged functionality with non-local routing.<n>These results motivate mode-conditional and stability-aware analyses as more reliable tools for interpreting and improving latent reasoning systems.
  arXiv  Detail & Related papers  (2026-02-09T15:25:12Z)
• CausalAffect: Causal Discovery for Facial Affective Understanding [26.904783570786773]
  CausalAffect is the first framework for causal graph discovery in facial affect analysis.<n>Our approach requires neither jointly annotated datasets nor handcrafted causal priors.<n>All trained models and source code will be released upon acceptance.
  arXiv  Detail & Related papers  (2025-11-29T12:07:33Z)
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models [55.30555646945055]
  Text-to-Image (T2I) models are vulnerable to semantic leakage.<n>We introduce DeLeaker, a lightweight approach that mitigates leakage by directly intervening on the model's attention maps.<n>SLIM is the first dataset dedicated to semantic leakage.
  arXiv  Detail & Related papers  (2025-10-16T17:39:21Z)
• Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models [4.946483489399819]
  Large Language Models (LLMs) are prone to hallucination, the generation of factually incorrect statements.<n>This work investigates the intrinsic, architectural origins of this failure mode through three primary contributions.
  arXiv  Detail & Related papers  (2025-10-07T16:40:31Z)
• LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components [0.17188280334580197]
  Large Language Models (LLMs) often display overconfidence, presenting information with unwarranted certainty in high-stakes contexts.<n>We use open-sourced Llama 3.2 models fine-tuned on human annotated assertiveness datasets.<n>Our analysis identifies layers most sensitive to assertiveness contrasts and reveals that high-assertive representations decompose into two sub-components of emotional and logical clusters.
  arXiv  Detail & Related papers  (2025-08-24T01:43:48Z)
• Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning [53.25336975467293]
  We present the first theoretical error decomposition analysis of methods such as perplexity and self-consistency.<n>Our analysis reveals a fundamental trade-off: perplexity methods suffer from substantial model error due to the absence of a proper consistency function.<n>We propose Reasoning-Pruning Perplexity Consistency (RPC), which integrates perplexity with self-consistency, and Reasoning Pruning, which eliminates low-probability reasoning paths.
  arXiv  Detail & Related papers  (2025-02-01T18:09:49Z)
• Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysis [56.84237932819403]
  This paper aims to estimate and mitigate the bad effect of textual modality for strong OOD generalization. Inspired by this, we devise a model-agnostic counterfactual framework for multimodal sentiment analysis.
  arXiv  Detail & Related papers  (2022-07-24T03:57:40Z)
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective [72.55093886515824]
  We introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables. We devise a modular architecture that factorizes the representations of invariant mechanisms and style confounders to approximate a causal graph. Experiment results on synthetic and real datasets show that our three proposed components significantly improve the robustness and reusability of the learned motion representations.
  arXiv  Detail & Related papers  (2021-11-29T18:59:09Z)
• Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
  Causal mechanisms can be described by structural causal models. One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
  arXiv  Detail & Related papers  (2021-09-06T14:52:58Z)
• Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA [81.4991350761909]
  Independent component analysis (ICA) refers to an ensemble of methods which formalize this goal and provide estimation procedure for practical application. We show that the latent variables can be recovered up to a permutation if one regularizes the latent mechanisms to be sparse.
  arXiv  Detail & Related papers  (2021-07-21T14:22:14Z)
• Disentangling Observed Causal Effects from Latent Confounders using Method of Moments [67.27068846108047]
  We provide guarantees on identifiability and learnability under mild assumptions. We develop efficient algorithms based on coupled tensor decomposition with linear constraints to obtain scalable and guaranteed solutions.
  arXiv  Detail & Related papers  (2021-01-17T07:48:45Z)
• Causal Autoregressive Flows [4.731404257629232]
  We highlight an intrinsic correspondence between a simple family of autoregressive normalizing flows and identifiable causal models. We exploit the fact that autoregressive flow architectures define an ordering over variables, analogous to a causal ordering, to show that they are well-suited to performing a range of causal inference tasks.
  arXiv  Detail & Related papers  (2020-11-04T13:17:35Z)
• The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions [93.62888099134028]
  We find that the performance of state-of-the-art models on Natural Language Inference (NLI) and Reading (RC) analysis/stress sets can be highly unstable. This raises three questions: (1) How will the instability affect the reliability of the conclusions drawn based on these analysis sets? We give both theoretical explanations and empirical evidence regarding the source of the instability.
  arXiv  Detail & Related papers  (2020-04-28T15:41:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.