ICML Paper: Trustworthiness of LLM Self-Explanations
_rockt · x · 2026-07-03
The ICML 2026 BOLD paper "A Positive Case for Faithfulness: LLM Self-Explanation," led by Harry Mayne and Justin Kangs, explores the trustworthiness of large language model self-explanations, presenting a positive argument for their reliability.
More from Research
- Exponential launches RepoInject and BrowserInject benchmarks for prompt injection robustness — maksym_andr · 2026-10-27
- Odd eval result: Gemini 4.1 Flash gets more accurate when asked to control its CoT — dfrsrchtwts · 2026-10-27
- Redwood: CoT controllability evals are under-elicited; better prompts boost scores 2-3x — dfrsrchtwts · 2026-10-27
- Inverse-designed optical system solves MNIST using BeamZ — S_Conradi · 2026-10-27
- DeCert supervises generative reward models' rationales without reference explanations — Guiquan Sun · 2026-10-27
- VLM harnesses act as compositional generalizers, new blog post shows — a1zhang · 2026-10-27