arXiv (All)
open access
Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation
Modern language models fail a fundamental requirement of trustworthy intelligence: knowing when not to answer. Despite achieving impressive accuracy on benchmarks, these models produce confident hallucinations, even when wrong answers carry catastrophic consequences. Our evaluations on GSM8K, MedQA
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Do Not Train Away Uncertainty: Early Uncertainty Anchored Calibration#1249473
- Linear Separability of Activation Representations after Supervised Fine-Tuning on Incorrect Responses: A Study of Synthetic Dishonesty in Large Language Models#973192
- The analysis of competing hypotheses and expert witness testimony: Counteracting adversarial allegiance in witness credibility assessments?#130476
- The analysis of competing hypotheses and expert witness testimony: Counteracting adversarial allegiance in witness credibility assessments?#120214
- Generating Chest X-Ray Counterfactuals by Specialising Foundation Image Models#1051277
Record · ID 1216205
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive