Cover Image

TruthFlow: Truthful LLM Generation via Representation Flow Correction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Hanyu, Cao, Bochuan, Cao, Yuanpu, Chen, Jinghui
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
by: Cao, Bochuan, et al.
Published: (2023)

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
by: Cao, Yuanpu, et al.
Published: (2023)

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
by: Wei, Zhepei, et al.
Published: (2025)

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
by: Cao, Bochuan, et al.
Published: (2025)

The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
by: Lan, Yifan, et al.
Published: (2026)

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
by: Zhang, Shaolei, et al.
Published: (2024)

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
by: Cao, Yuanpu, et al.
Published: (2024)

Soft Tokens, Hard Truths
by: Butt, Natasha, et al.
Published: (2025)

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
by: Xu, Haoming, et al.
Published: (2026)

The Geometries of Truth Are Orthogonal Across Tasks
by: Azizian, Waiss, et al.
Published: (2025)

Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
by: Liu, Zehao, et al.
Published: (2026)

JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution
by: Chang, Yurui, et al.
Published: (2024)

Ranking Large Language Models without Ground Truth
by: Dhurandhar, Amit, et al.
Published: (2024)

Personas as a Way to Model Truthfulness in Language Models
by: Joshi, Nitish, et al.
Published: (2023)

Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models
by: Liang, Kaiqu, et al.
Published: (2025)

Overthinking the Truth: Understanding how Language Models Process False Demonstrations
by: Halawi, Danny, et al.
Published: (2023)

When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs
by: Wang, Shaowen, et al.
Published: (2025)

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
by: Li, Kenneth, et al.
Published: (2023)

Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models
by: Rahman, Subhey Sadi, et al.
Published: (2025)

From Ground Truth to Measurement: A Statistical Framework for Human Labeling
by: Chew, Robert, et al.
Published: (2026)

How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
by: Du, Hongzhe, et al.
Published: (2025)

WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
by: Zhang, Tianrong, et al.
Published: (2024)

TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability
by: Khatun, Aisha, et al.
Published: (2024)

Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries
by: Hicke, Rebecca M. M., et al.
Published: (2026)

On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models
by: Goel, Naman
Published: (2023)

LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
by: Liu, Zihang, et al.
Published: (2025)

DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding
by: Zhang, Ruiyi, et al.
Published: (2025)

FlowRL: Matching Reward Distributions for LLM Reasoning
by: Zhu, Xuekai, et al.
Published: (2025)

Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows
by: Zhang, Shujian, et al.
Published: (2024)

FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
by: Li, Zhuoyun, et al.
Published: (2026)

AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
by: Zeng, Yaopei, et al.
Published: (2024)

Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs
by: Cattaneo, Alberto, et al.
Published: (2025)

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
by: Adarsh, Shivam, et al.
Published: (2026)

Jump Starting Bandits with LLM-Generated Prior Knowledge
by: Alamdari, Parand A., et al.
Published: (2024)

Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
by: Chang, Yurui, et al.
Published: (2025)

Your Agent Can Defend Itself against Backdoor Attacks
by: Changjiang, Li, et al.
Published: (2025)

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
by: Sun, Lihao, et al.
Published: (2026)

The Geometry of Reasoning: Flowing Logics in Representation Space
by: Zhou, Yufa, et al.
Published: (2025)

AgentInstruct: Toward Generative Teaching with Agentic Flows
by: Mitra, Arindam, et al.
Published: (2024)

Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
by: Li, Yawei, et al.
Published: (2026)