COLM 2026 interpretability lineup: reasoning unlocks parametric knowledge, and more
megamor2 · x · 2026-10-05
A researcher rounds up their group's COLM 2026 papers on LLM interpretability, including "Thinking to Recall" on how reasoning unlocks parametric knowledge, "Disentangling MLP Neuron Weights in Vocabulary Space," and a spotlight oral on unification forces in generalization dynamics, plus the 2nd Actionable Interpretability Workshop.
More from Research
- MemAdapter uses counterfactual reasoning to curb memory-induced sycophancy in LLM agents — Ruqing Ning · 2026-10-06
- Peking University's Code2Games gets coding agents to build playable UE5 game worlds — PekingUniversity · 2026-10-06
- QuantCode: domain pretraining + SFT lifts Qwen trading-code pass from 27.8% to 58.2% — Alexey Chernysh · 2026-10-06
- Subsampling and extrapolation keep the Mandelbrot area estimate unbiased near the boundary — geoffreyirving · 2026-10-06
- Group-Evolving Agents: a new paradigm where the unit of agent self-improvement is a group — xwang_lk · 2026-10-06
- SLIM paper at COLM: design principles for long-horizon agentic search systems — xiye_nlp · 2026-10-06