Polar probe paper accepted at COLM 2026: linearly decoding semantic geometry in LLMs
JeanRemiKing · x · 2026-10-07
"Polar probe linearly decodes semantic structures from LLMs" has been accepted at COLM 2026. The team (itspablit0, PierreOrhan, Emmanuel Chemla, lakretz, JeanRemiKing) finds a simple geometry for semantic structures inside LLMs, showing a linear probe can decode semantic organization from model representations — an interpretability result with a thread of details.
More from Research
- Mathematician: norms for LLM use in serious math are still unsettled — littmath · 2026-10-07
- IdeaLens debuts: a detector that separates human ideas from AI-written prose — MohitIyyer · 2026-10-07
- SC4AI'27 workshop on social choice for AI alignment at AAAI, deadline Nov 20 — conitzer · 2026-10-07
- Grafting mid-training weights onto RLed models works, challenging the PSM pipeline — repligate · 2026-10-07
- WonderSearch 1.1 claims #1 on all 7 sparse retrieval benchmarks, no vector DB needed — Scobleizer · 2026-10-07
- NIH Pioneer Award grants ~$6M for LLM agents generating cancer hypotheses tested by robots — anshulkundaje · 2026-10-07