EMNLP 2026 interpretability tutorial slides released, praised by attendees
PMinervini · x · 2026-11-03
Researchers led by @amuuueller, with collaborators @rpatrik96, @shrutijoshi and @dhanyasridhar, released the slides for their #EMNLP2026 tutorial on putting interpretability on more rigorous foundations. Reposting, @gsarti says every EMNLP attendee he talked to was blown away by the tutorial's quality. Recommended for newcomers and experts alike; slides linked in the original post.
More from Research
- Meta FAIR paper: research agents work best with humans, hack detection still weak — armand_ruiz · 2026-11-03
- Stanford Re-tests 50 Widely Cited LLM Findings: Most Expire or Fade Within 15 Months — ziv_ravid · 2026-11-03
- SafeTulu: scalable gradient attribution filters benign-looking data that erodes LLM safety — pratyushmaini · 2026-11-03
- MIT shows LLMs can natively edit weights: 0.016% change lifts MATH-500 from 7.9% to 48.1% — lateinteraction · 2026-11-03
- Compute-matched study: synthetic pre-pretraining never beats natural language — LauraRuis · 2026-11-03
- Apple's iPrefBench tests personal agents on 130 underspecified iOS tasks: infer or ask? — hhsun1 · 2026-11-03