Researchers debate whether LLMs need token-for-token conditioning to generalize
srush_nlp · x · 2026-07-23
A discussion about whether token-for-token conditioning is really necessary in LLM training.
One side says the harness argument is plausible, but token-level conditioning seems unlikely to be the whole story because LLMs already show strong input generalization beyond exact training patterns.
Related event: LLM Generalization Debate: Intrinsic Model or Harness Contribution?(11 posts)→
More from Research
- MaP-WAM tackles non-Markovian robot manipulation with memory-grounded planning — Sizhe Zhao · 2026-09-11
- Negative Self-Distillation improves LLM reasoning by avoiding flawed reasoning paths — Rongcan Pei · 2026-09-11
- ~25% of NBER economics papers now contain AI-generated text, study finds — JeremyNguyenPhD · 2026-09-11
- DeepMind-led paper makes design docs the source of truth, code disposable — SMART regenerates in 1.5-3h for ~$100 — Roger_M_Taylor · 2026-09-11
- GameWorld wins Best Paper Runner-Up at ECCV 2026 Multimodal Digital Agents Workshop — MikeShou1 · 2026-09-11
- Yann LeCun live at ECCV on World Models — Weak_Assistance_5261 · 2026-09-11