Cover Image

The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yubo, Krishnan, Ramayya, Padman, Rema
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG
by: Li, Yubo, et al.
Published: (2026)

Consistency of Large Reasoning Models Under Multi-Turn Attacks
by: Li, Yubo, et al.
Published: (2026)

Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
by: Li, Yubo, et al.
Published: (2025)

When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models
by: Li, Yubo, et al.
Published: (2026)

Chain-of-Influence: Tracing Interdependencies Across Time and Features in Clinical Predictive Modelings
by: Li, Yubo, et al.
Published: (2025)

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
by: Li, Yubo, et al.
Published: (2026)

Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions
by: Li, Yubo, et al.
Published: (2025)

Closing Reasoning Gaps in Clinical Agents with Differential Reasoning Learning
by: Liu, Jinsong, et al.
Published: (2026)

Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
by: Li, Yubo, et al.
Published: (2025)

No Black Box Anymore: Demystifying Clinical Predictive Modeling with Temporal-Feature Cross Attention Mechanism
by: Li, Yubo, et al.
Published: (2025)

Towards Interpretable End-Stage Renal Disease (ESRD) Prediction: Utilizing Administrative Claims Data with Explainable AI Techniques
by: Li, Yubo, et al.
Published: (2024)

Correct Chains, Wrong Answers: Dissociating Reasoning from Output in LLM Logic
by: Rao, Abinav, et al.
Published: (2026)

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
by: Xu, Rongwu, et al.
Published: (2024)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
by: Wang, Changsheng, et al.
Published: (2025)

Enhancing End Stage Renal Disease Outcome Prediction: A Multi-Sourced Data-Driven Approach
by: Li, Yubo, et al.
Published: (2024)

Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answers
by: Rueda, Alice, et al.
Published: (2025)

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction
by: Zhang, Chen, et al.
Published: (2026)

Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models
by: Wang, Yuhui, et al.
Published: (2025)

Plantain: Plan-Answer Interleaved Reasoning
by: Liang, Anthony, et al.
Published: (2025)

VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection
by: Petullo, James, et al.
Published: (2026)

Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces
by: He, Chen, et al.
Published: (2026)

Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners
by: Pandey, Rohan, et al.
Published: (2026)

Reasoning about Study Regulations in Answer Set Programming
by: Hahn, Susana, et al.
Published: (2024)

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
by: Chen, Haoyang, et al.
Published: (2026)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

Counting Answer Sets of Disjunctive Answer Set Programs
by: Kabir, Mohimenul, et al.
Published: (2025)

Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
by: Abdaljalil, Samir, et al.
Published: (2026)

Can LLMs Support Medical Knowledge Imputation? An Evaluation-Based Perspective
by: Yao, Xinyu, et al.
Published: (2025)

Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models
by: Liu, Shuliang, et al.
Published: (2026)

Answer Set Programming Modulo Theories and Reasoning about Continuous Changes
by: Lee, Joohyung, et al.
Published: (2025)

Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning
by: Jiang, Enyi, et al.
Published: (2025)

From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization
by: Wang, Beining, et al.
Published: (2025)

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
by: Cao, Chentao, et al.
Published: (2025)

A framework for Conditional Reasoning in Answer Set Programming
by: Alviano, Mario, et al.
Published: (2025)

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
by: Kim, Kyuyoung, et al.
Published: (2026)

Implicit Probabilistic Reasoning Does Not Reflect Explicit Answers in Large Language Models
by: Mondal, Manuel, et al.
Published: (2024)

Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning
by: Jo, Hwiyeol, et al.
Published: (2025)

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
by: Wiegreffe, Sarah, et al.
Published: (2024)

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models
by: Zheng, Baihui, et al.
Published: (2025)

Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models
by: Zhan, Yufei, et al.
Published: (2025)