Using Internal Probes for RL Rewards
burny_tech · x · 2026-07-15
GoodfireAI introduced RLFR: using a model's internal probe as a reinforcement learning reward signal to train the model to hallucinate less.
Reposts mention that Silico replicated this method 2 天内, claiming to have reduced the hallucination rate by 37% on Qwen3-8B without any loss of capability.
Related event: RLFR Method Uses Internal Probes to Reduce LLM Hallucinations by 37%(3 posts)→
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