Cover Image

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Swaroop, Anand, Nallani, Akshat, Uboweja, Saksham, Uzdenova, Adiliia, Nguyen, Michael, Zhu, Kevin, Dev, Sunishchal, Panda, Ashwinee, Sharma, Vasu, Chaudhary, Maheep
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
by: Batra, Shourya, et al.
Published: (2025)

Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization
by: Egbuna, Nathan, et al.
Published: (2025)

Peek-a-Boo Reasoning: Contrastive Region Masking in MLLMs
by: Chaturvedi, Isha, et al.
Published: (2025)

Evaluation Awareness Scales Predictably in Open-Weights Large Language Models
by: Chaudhary, Maheep, et al.
Published: (2025)

Broken Chains: The Cost of Incomplete Reasoning in LLMs
by: Su, Ian, et al.
Published: (2026)

Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits
by: Patel, Dev, et al.
Published: (2025)

PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases
by: Vuddanti, Sri Vatsa, et al.
Published: (2025)

Thought Experiments in Design Fiction for Visualization
by: Panda, Swaroop
Published: (2024)

Modeling and Predicting Multi-Turn Answer Instability in Large Language Models
by: He, Jiahang, et al.
Published: (2025)

Hydra: A Modular Architecture for Efficient Long-Context Reasoning
by: Chaudhary, Siddharth, et al.
Published: (2025)

Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals
by: Li, Sophie, et al.
Published: (2025)

In-Context Environments Induce Evaluation-Awareness in Language Models
by: Chaudhary, Maheep
Published: (2026)

Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis
by: More, Abhishek, et al.
Published: (2025)

DuoLens: A Framework for Robust Detection of Machine-Generated Multilingual Text and Code
by: Agrawal, Shriyansh, et al.
Published: (2025)

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs
by: Thomas, Rohan Subramanian, et al.
Published: (2026)

A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy
by: O'Brien, Claire, et al.
Published: (2026)

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors
by: Chaudhary, Maheep, et al.
Published: (2025)

Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small
by: Chaudhary, Maheep, et al.
Published: (2024)

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
by: Mittal, Avni, et al.
Published: (2026)

Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
by: Nunez, Jeanmely Rojas, et al.
Published: (2026)

AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI
by: Rana, Manik, et al.
Published: (2025)

SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models
by: Lv, Weijiang, et al.
Published: (2026)

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
by: Afonin, Nikita, et al.
Published: (2025)

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
by: Paul, Debjit, et al.
Published: (2024)

Confidential FRIT via Homomorphic Encryption
by: Hoshino, Haruki, et al.
Published: (2025)

LLMs' ways of seeing User Personas
by: Panda, Swaroop
Published: (2024)

Making AI Agents Evaluate Misleading Charts without Nudging
by: Panda, Swaroop
Published: (2026)

Look into your Heart -- Prototypes for a Speculative Design Exploration of Personal Heart Rate Visualization
by: Panda, Swaroop
Published: (2025)

A Framework for LLM-powered Design Assistants
by: Panda, Swaroop
Published: (2025)

Physical therapeutic elements in stage medical recovery of puerperas
by: Zukhra Kh. Uzdenova
Published: (2021)

Physical therapeutic factors in stage medical rehabilitation of puerperas with perineal wounds after fetal vacuum extraction
by: Zukhra Kh. Uzdenova
Published: (2021)

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
by: Jia, Jinghan, et al.
Published: (2026)

Counterfactual Simulation Training for Chain-of-Thought Faithfulness
by: Hase, Peter, et al.
Published: (2026)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
by: Arcuschin, Iván, et al.
Published: (2025)

@GrokSet: multi-party Human-LLM Interactions in Social Media
by: Migliarini, Matteo, et al.
Published: (2026)

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
by: Zaman, Kerem, et al.
Published: (2025)

Sumudu Neural Operator for ODEs and PDEs
by: Zelenskiy, Ben, et al.
Published: (2025)

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
by: Yu, Xiangning, et al.
Published: (2025)

Freespace twistronics for optical supertopologies
by: Dev, Vasu, et al.
Published: (2025)

GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought
by: Lv, Weijiang, et al.
Published: (2026)