The paper behind the EMNLP 2026 keynote on bigram 'simulated learners'
najoungkim · x · 2026-10-26
Najoung Kim points to their paper explaining the 'simulated learners' line of work behind the EMNLP 2026 keynote. The keynote frames LLMs as instruments in three ways: simulated learners (controlled-input training like BabyLM, impossible languages), models of mind and brain (surprisal predicting reading times, representations predicting brain responses), and AI scientists — with the caveat that LLMs are neither children nor brains, and value comes from controlled comparison with humans.
More from Research
- Kolab Benchmark Uses Pro Screen Recordings to Show AI Agents Overestimate Collaboration Quality — minnesotanlp · 2026-10-27
- One BBQ Example Pushes LLM Fairness Scores Past 90%, EMNLP Paper Questions Benchmarks — radamihalcea · 2026-10-27
- Real2Sem2Real turns one phone video into 2,000+ robot demos, matching 150 teleop demos — Scobleizer · 2026-10-27
- Understanding MuonH (Hyperball) through weight norm geometry of scale-invariant networks — jasondeanlee · 2026-10-27
- Sail equivalence proof and riscv-coq cross-checks uncover real RISC-V spec bugs — xennygrimmato_ · 2026-10-27
- Kokotajlo challenges CoT monitorability evals: what if the model didn't refuse? — dfrsrchtwts · 2026-10-27