EMNLP Talk to Present RELIC, a Framework for Peering Inside Closed-Trace Reasoning Models
tallinzen · x · 2026-10-09
jowenpetty announced an EMNLP talk (Oct 26, 11am, room F8, Budapest) introducing RELIC, a framework for peering into the inner workings of closed-trace reasoning models like Fable and Astra.
The approach combines methods from computational linguistics and theoretical computer science to make closed reasoning traces interpretable.
More from Research
- COLM 2026's GenAI4World workshop tackles globalizing AI tasks, evals, and systems — m2saxon · 2026-10-09
- Rao talks 'mythos of thinking traces' at Max Planck Tübingen, slides and audio public — rao2z · 2026-10-09
- First All-Atom Protein Design Model Controllable by Natural Language Unveiled — PangWeiKoh · 2026-10-09
- 8 Lean Formalizations in OpenAI's Repo 'Broken' — Wrong Proofs Pass Verification — AlexTensor · 2026-10-09
- COLM 2026 Actionable Interpretability Workshop Accepts 71 Papers, Posters Online — ChrisGPotts · 2026-10-09
- Meta paper introduces 'agent plasticity': measuring self-improving agent gains per dollar spent on learning — omarsar0 · 2026-10-09