Meta paper argues truth is invariance, not likelihood, for LLMs
dair_ai · x · 2026-11-15
Meta FAIR's David Lopez-Paz published "Against All Likelihood", arguing maximum likelihood is a category error as a proxy for truth: unlikely events happen daily, and lies repeated often become highly probable yet false. Drawing on Nozick, Poincaré and Cassirer, the essay ties objectivity to invariance across relevant transformations, connects this to OOD generalization and invariant learning, sketches how an LLM could test invariance at inference time, and suggests continual-learning agents should keep only claims that hold across settings.
More from Research
- Google's new AIS team unveils DuoDiscover with 4.09x kernel speedups and LEAP formalizing Weil conjectures — VioletNPeng · 2026-11-15
- Compositional reasoning under RL post-training paper accepted to NeurIPS 2026 — yifeiwang77 · 2026-11-15
- How EmbeddingGemma 2 is trained: staged Gemini distillation down to 128-dim Matryoshka embeddings — gabriberton · 2026-11-15
- EmbeddingGemma 2 topped HuggingFace trending for a week, a spot usually held by LLMs — gabriberton · 2026-11-15
- SJTU's Value-as-Memory Gives Robot Policies Task-Progress Memory, +29.4pp on Real Tasks — jiqizhixin · 2026-11-15
- Genesis Team Launches Eden, a Robot Learning Framework That Builds Tasks 1.6-4x Faster Than Isaac Lab — zhou_xian_ · 2026-11-15