Image de couverture de livre

Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mohamadi, Mohamad Amin, Wang, Tianhao, Li, Zhiyuan
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity
par: Xie, Shuo, et autres
Publié: (2024)

Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition
par: Mohamadi, Mohamad Amin, et autres
Publié: (2024)

The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
par: Ren, Richard, et autres
Publié: (2025)

Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
par: McKee-Reid, Leo, et autres
Publié: (2024)

Training LLMs for Honesty via Confessions
par: Joglekar, Manas, et autres
Publié: (2025)

EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models
par: Tamo, J. Ben, et autres
Publié: (2026)

How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
par: Liu, Ryan, et autres
Publié: (2024)

Honesty in Causal Forests: When It Helps and When It Hurts
par: Hou, Yanfang, et autres
Publié: (2025)

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
par: Yang, Jinluan, et autres
Publié: (2025)

Provable Benefit of Sign Descent: A Minimal Model Under Heavy-Tailed Class Imbalance
par: Yadav, Robin, et autres
Publié: (2025)

A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent
par: Xie, Shuo, et autres
Publié: (2025)

Relative Kinetic Utility for Reasoning-Aware Structural Pruning in Large Language Models
par: Qian, Tianhao
Publié: (2026)

Know your Trajectory -- Trustworthy Reinforcement Learning deployment through Importance-Based Trajectory Analysis
par: F, Clifford, et autres
Publié: (2025)

Preference Learning with Lie Detectors can Induce Honesty or Evasion
par: Cundy, Chris, et autres
Publié: (2025)

Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
par: Gu, Renjie, et autres
Publié: (2026)

Structured Preconditioners in Adaptive Optimization: A Unified Analysis
par: Xie, Shuo, et autres
Publié: (2025)

Incentivizing Honesty among Competitors in Collaborative Learning and Optimization
par: Dorner, Florian E., et autres
Publié: (2023)

AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations
par: Clark, Michael J.
Publié: (2026)

The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
par: Taufeeque, Mohammad, et autres
Publié: (2026)

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models
par: Mo, Yichuan, et autres
Publié: (2026)

The Marginal Value of Momentum for Small Learning Rate SGD
par: Wang, Runzhe, et autres
Publié: (2023)

Enhanced High-Dimensional Data Visualization through Adaptive Multi-Scale Manifold Embedding
par: Ni, Tianhao, et autres
Publié: (2025)

Think Before You Lie: How Reasoning Leads to Honesty
par: Yuan, Ann, et autres
Publié: (2026)

Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization
par: Yuan, Haochen, et autres
Publié: (2025)

PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning
par: Gong, Chen, et autres
Publié: (2025)

TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents
par: Gong, Chen, et autres
Publié: (2024)

Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
par: Pawelczyk, Martin, et autres
Publié: (2024)

Beyond Accuracy: On the Effects of Fine-tuning Towards Vision-Language Model's Prediction Rationality
par: Wang, Qitong, et autres
Publié: (2024)

Trustworthy Classification through Rank-Based Conformal Prediction Sets
par: Luo, Rui, et autres
Publié: (2024)

HARP: Hesitation-Aware Reframing in Transformer Inference Pass
par: Storaï, Romain, et autres
Publié: (2024)

Strong Transitivity Relations and Graph Neural Networks
par: Mohamadi, Yassin, et autres
Publié: (2024)

Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models
par: Pan, Jiazhen, et autres
Publié: (2025)

CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
par: Xia, Peng, et autres
Publié: (2024)

Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
par: Liu, Yang, et autres
Publié: (2023)

Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting
par: Kang, James Jin, et autres
Publié: (2025)

Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems
par: Dearstyne, Katherine, et autres
Publié: (2025)

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
par: Hou, Zhenyu, et autres
Publié: (2025)

A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions
par: Liu, Lei, et autres
Publié: (2024)

AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving
par: Xing, Shuo, et autres
Publié: (2024)

Open-World Reinforcement Learning over Long Short-Term Imagination
par: Li, Jiajian, et autres
Publié: (2024)