Image de couverture de livre

Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Peng, Guangyue, Chen, Zongchao, Luo, Wen, Wen, Yuntao, Li, Wei, Feng, Ruixiang, Le, Ran, Yang, Chen, An, Zhenwei, Song, Yang, Zhang, Tao, Wang, Houfeng
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

Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts
par: Yang, Chen, et autres
Publié: (2026)

CoSineVerifier: Tool-Augmented Answer Verification for Computation-Oriented Scientific Questions
par: Feng, Ruixiang, et autres
Publié: (2025)

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning
par: Feng, Ruixiang, et autres
Publié: (2026)

Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction
par: Li, Wei, et autres
Publié: (2025)

Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation
par: Luo, Wen, et autres
Publié: (2025)

Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models
par: Yang, Chen, et autres
Publié: (2025)

ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset
par: Yang, Chen, et autres
Publié: (2025)

HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation
par: Luo, Wen, et autres
Publié: (2024)

Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
par: Luo, Wen, et autres
Publié: (2026)

FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation
par: Li, Wei, et autres
Publié: (2025)

CoRGI: Verified Chain-of-Thought Reasoning with Post-hoc Visual Grounding
par: Yi, Shixin, et autres
Publié: (2025)

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
par: Lewis-Lim, Samuel, et autres
Publié: (2025)

RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning
par: Xu, Song, et autres
Publié: (2025)

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
par: Song, Huatong, et autres
Publié: (2026)

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
par: Luo, Wen, et autres
Publié: (2026)

Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs
par: Ahrend, Patrick, et autres
Publié: (2026)

Markov Chain of Thought for Efficient Mathematical Reasoning
par: Yang, Wen, et autres
Publié: (2024)

Efficient and Stable 0D Cs3Cu2Br5:Mn Single Crystals for Low‐Dose High‐Resolution X‐Ray Imaging
par: Yujie Wang, et autres
Publié: (2025)

Chain of Event-Centric Causal Thought for Physically Plausible Video Generation
par: Wang, Zixuan, et autres
Publié: (2026)

Spatial Chain-of-Thought: Bridging Understanding and Generation Models for Spatial Reasoning Generation
par: Chen, Wei, et autres
Publié: (2026)

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization
par: Huang, Yu, et autres
Publié: (2025)

Post-hoc Bias Scoring Is Optimal For Fair Classification
par: Chen, Wenlong, et autres
Publié: (2023)

Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection
par: He, Chaoqun, et autres
Publié: (2026)

Mitigating Overthinking through Reasoning Shaping
par: Song, Feifan, et autres
Publié: (2025)

Before the Shutter: Aesthetic and Actionable Portrait Photography Planning in 3D Scenes
par: Jiang, Ruixiang, et autres
Publié: (2026)

ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing
par: Liu, Huadai, et autres
Publié: (2025)

Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning
par: Chang, Wen-Yu, et autres
Publié: (2024)

Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
par: Ma, Ji, et autres
Publié: (2026)

PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation
par: Liu, Huadai, et autres
Publié: (2025)

SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing
par: Zhang, Ruiyang, et autres
Publié: (2025)

An Analysis and Mitigation of the Reversal Curse
par: Lv, Ang, et autres
Publié: (2023)

PXGen: A Post-hoc Explainable Method for Generative Models
par: Huang, Yen-Lung, et autres
Publié: (2025)

When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors
par: Chen, Shiwei, et autres
Publié: (2026)

Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models
par: Ma, Qihang, et autres
Publié: (2025)

Chain-of-Thought Re-ranking for Image Retrieval Tasks
par: Wu, Shangrong, et autres
Publié: (2025)

SWE-World: Building Software Engineering Agents in Docker-Free Environments
par: Sun, Shuang, et autres
Publié: (2026)

Post-hoc Part-prototype Networks
par: Tan, Andong, et autres
Publié: (2024)

Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuning
par: Chen, Xinhao, et autres
Publié: (2024)

Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
par: Deng, Linger, et autres
Publié: (2024)

FedCoT: Federated Chain-of-Thought Distillation for Large Language Models
par: Fan, Tao, et autres
Publié: (2024)