Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yan, Tianqiang, Shang, Sihan, Li, Yuheng, Qiu, Song, Peng, Hao, Luo, Wenjian, Xie, Jue, Qu, Lizhen, Gao, Yuan
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data
par: Feng, Tao, et autres
Publié: (2025)

Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search
par: Huang, Shuo, et autres
Publié: (2025)

Does Competing‐Risk Modelling Appropriately Reflect the Bridging Role of Early RRT in Cirrhosis?
par: Tianqiang Sheng, et autres
Publié: (2026)

Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
par: Shi, Yuheng, et autres
Publié: (2024)

Letter to the Editor: Beyond Perception: Translating Insights on Gender Discrimination in Nursing Into Actionable Change
par: Tianqiang Sheng, et autres
Publié: (2025)

Re-ReST: Reflection-Reinforced Self-Training for Language Agents
par: Dou, Zi-Yi, et autres
Publié: (2024)

Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification
par: Ji, Ke, et autres
Publié: (2024)

CausalScore: An Automatic Reference-Free Metric for Assessing Response Relevance in Open-Domain Dialogue Systems
par: Feng, Tao, et autres
Publié: (2024)

Position: A Potential Outcomes Perspective on Pearl's Causal Hierarchy
par: Wu, Peng, et autres
Publié: (2026)

Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
par: Huang, Jiahao, et autres
Publié: (2026)

Combating Spurious Correlations in Graph Interpretability via Self-Reflection
par: Cai, Kecheng, et autres
Publié: (2026)

On the Reliability of Large Language Models for Causal Discovery
par: Feng, Tao, et autres
Publié: (2024)

A Self-scaled Approximate $\ell_0$ Regularization Robust Model for Outlier Detection
par: Song, Pengyang, et autres
Publié: (2025)

DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement
par: Lin, Shaoqing, et autres
Publié: (2025)

Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression
par: Luo, Zhankun, et autres
Publié: (2024)

Reflections on the Need for Hierarchies in Bioethical Principialism
par: Roberto Israel Rodríguez Soriano
Publié: (2018)

CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing
par: Xian, Xiaole, et autres
Publié: (2024)

Dynamic changes of net anthropogenic nitrogen/phosphorus input and its riverine export in the Beijing's subcenter
par: Xiaoyu Luo, et autres
Publié: (2024)

Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons
par: Wang, Yifei, et autres
Publié: (2024)

ReCA: A Parametric ReLU Composite Activation Function
par: Chidiac, John, et autres
Publié: (2025)

To disclose or not to disclose: Peer influence and psychological factors in students' use of generative artificial intelligence
par: Yao Qu, et autres
Publié: (2026)

Imperative MPC: An End-to-End Self-Supervised Learning with Differentiable MPC for UAV Attitude Control
par: He, Haonan, et autres
Publié: (2025)

Biokarst_CA_Dataset
par: Xie, Tengxiang
Publié: (2025)

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
par: Wu, Penghao, et autres
Publié: (2025)

SurvReLU: Inherently Interpretable Survival Analysis via Deep ReLU Networks
par: Sun, Xiaotong, et autres
Publié: (2024)

Self-Dual Electrodynamics via the Characteristic Method: Relativistic and Carrollian Perspectives
par: Chen, Bin, et autres
Publié: (2025)

Self-covering, finiteness, commutativity, and fibering over tori
par: Qin, Lizhen, et autres
Publié: (2025)

Iterative Self-Training for Code Generation via Reinforced Re-Ranking
par: Sorokin, Nikita, et autres
Publié: (2025)

Unveiling Interpretability in Self-Supervised Speech Representations for Parkinson's Diagnosis
par: Gimeno-Gómez, David, et autres
Publié: (2024)

Identifiability in Causal Abstractions: A Hierarchy of Criteria
par: Yvernes, Clément, et autres
Publié: (2025)

Gateways to Tractability for Satisfiability in Pearl's Causal Hierarchy
par: Ganian, Robert, et autres
Publié: (2025)

Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues
par: Hua, Yuncheng, et autres
Publié: (2024)

TAB-AUDIT: Detecting AI-Fabricated Scientific Tables via Multi-View Likelihood Mismatch
par: Huang, Shuo, et autres
Publié: (2026)

DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects
par: Xie, Guanghu, et autres
Publié: (2025)

Enhancing Financial Question Answering with a Multi-Agent Reflection Framework
par: Fatemi, Sorouralsadat, et autres
Publié: (2024)

Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding
par: Pereira, Joao, et autres
Publié: (2025)

Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications
par: Paul, Debdas, et autres
Publié: (2026)

Hybrid Causal Identification and Causal Mechanism Clustering
par: Liu, Saixiong, et autres
Publié: (2025)

Reliable Cross-modal Alignment via Prototype Iterative Construction
par: Ma, Xiang, et autres
Publié: (2025)

Textual-to-Visual Iterative Self-Verification for Slide Generation
par: Xu, Yunqing, et autres
Publié: (2025)