Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation

arXiv:2511.11500 · cs.LG · Submitted 2025-11-14 · Read on arXiv

cs.LG

Submitted: 2025-11-14

Updated: 2026-10-06

Terminology

• Abstention — 4× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Sources

• Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving
• Reasoning Models Don't Always Say What They Think
• Training Verifiers to Solve Math Word Problems
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
• Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline
• OpenAI o1 System Card
• Rewarding Intellectual Humility Learning When Not To Answer In Large Language Models
• Language Models (Mostly) Know What They Know
• Why Language Models Hallucinate
• BabyBear: Cheap inference triage for expensive language models
• Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning
• Taming Overconfidence in LLMs: Reward Calibration in RLHF
• Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
• Qwen3 Technical Report
• When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
• Measuring Epistemic Humility in Multimodal Large Language Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks