Cover Image

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Young, Richard J.
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence I.2.7; I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models
by: Ubukata, Shunsuke
Published: (2026)

Learned Relay Representations for Forward-Thinking Discrete Diffusion Models
by: Rozonoyer, Benjamin, et al.
Published: (2026)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
by: Fadli, Samih
Published: (2025)

The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models
by: Anderson, Samuel Cyrenius
Published: (2026)

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It
by: Garcia, Gabriel
Published: (2026)

Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring
by: Heyman, Alex, et al.
Published: (2025)

BitCal-TTS: Bit-Calibrated Test-Time Scaling for Quantized Reasoning Models
by: Patarlapalli, Sai Babu, et al.
Published: (2026)

Merge-Bench: Resolve Merge Conflicts with Large Language Models
by: Schesch, Benedikt, et al.
Published: (2026)

Automated Bug Triaging using Instruction-Tuned Large Language Models
by: Kiashemshaki, Kiana, et al.
Published: (2025)

Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction
by: Walker, Nicholas
Published: (2024)

Why LoRA Resists Label Noise: A Theoretical Framework for Noise-Robust Parameter-Efficient Fine-Tuning
by: Steele, Brady
Published: (2026)

Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols
by: Hu, Julia, et al.
Published: (2026)

When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs
by: Young, Richard J., et al.
Published: (2025)

Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs
by: Eisenstadt, Roy, et al.
Published: (2025)

Mixup Model Merge: Enhancing Model Merging Performance through Randomized Linear Interpolation
by: Zhou, Yue, et al.
Published: (2025)

Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models
by: Liao, Jianxing, et al.
Published: (2025)

Planning vs Reasoning: Ablations to Test Capabilities of LoRA layers
by: Redkar, Neel
Published: (2024)

Induce, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive Reasoning
by: Zhang, Bowen, et al.
Published: (2025)

TRiMS: Real-Time Tracking of Minimal Sufficient Length for Efficient Reasoning via RL
by: Bian, Tingcheng, et al.
Published: (2026)

Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales
by: Salfati, Samuel
Published: (2026)

KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models
by: Liu, Zhongxin, et al.
Published: (2025)

Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
by: Han, Xudong, et al.
Published: (2025)

Emergent Lexical Semantics in Neural Language Models: Testing Martin's Law on LLM-Generated Text
by: Kugler, Kai
Published: (2025)

Transformer Scalability Crisis: The First Comprehensive Empirical Analysis of Performance Walls in Modern Language Models
by: Moghadasi, Mahdi Naser, et al.
Published: (2026)

MCP: A Control-Theoretic Orchestration Framework for Synergistic Efficiency and Interpretability in Multimodal Large Language Models
by: Zhang, Luyan
Published: (2025)

Pre-trained Models Perform the Best When Token Distributions Follow Zipf's Law
by: He, Yanjin, et al.
Published: (2025)

Kronecker Embeddings: Byte-Level Structured Token Representations for Parameter-Efficient Language Models
by: Shravan, Rohan
Published: (2026)

Before the Last Token: Diagnosing Final-Token Safety Probe Failures
by: Doda, Shravan
Published: (2026)

Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents
by: Costa, Rimom
Published: (2025)

EmoLoom-2B: Fast Base-Model Screening for Emotion Classification and VAD with Lexicon-Weak Supervision and KV-Off Evaluation
by: Li, Zilin, et al.
Published: (2026)

Latent Cache Flow: Model-to-Model Communication Without Text
by: Rossi, Maximillian, et al.
Published: (2026)

Survey Transfer Learning: Recycling Data with Silicon Responses
by: Amini, Ali
Published: (2025)

Intention Collapse: Intention-Level Metrics for Reasoning in Language Models
by: Vera, Patricio
Published: (2026)

Cost-Aware Model Selection for Text Classification: Multi-Objective Trade-offs Between Fine-Tuned Encoders and LLM Prompting in Production
by: Gonzalez, Alberto Andres Valdes
Published: (2026)

On Semantic Loss Fine-Tuning Approach for Preventing Model Collapse in Causal Reasoning
by: Deshmukh, Pratik, et al.
Published: (2026)

Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning
by: Yang, Shan
Published: (2026)

HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
by: He, Yongquan, et al.
Published: (2024)

Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem Features
by: Heyman, Alex, et al.
Published: (2025)

Assessing Large Language Models on Islamic Legal Reasoning: Evidence from Inheritance Law Evaluation
by: Bouchekif, Abdessalam, et al.
Published: (2025)

What Language Models Know But Don't Say: Non-Generative Prior Extraction for Generalization
by: Rezaeimanesh, Sara, et al.
Published: (2026)