✳flâneur — a map of the web's best reading
instruction tuning and autoregressive distribution shift — LessWrong
lesswrong.com · 2,355 words · saved by 1 readers
[Note: this began life as a "Quick Takes" comment, but it got pretty long, so I figured I might as well convert it to a regular post.] …
x instruction tuning and autoregressive distribution shift — LessWrong AI Frontpage 41 instruction tuning and autoregressive distribution shift by nostalgebraist 5th Sep 2024 6 min read 5 41 [Note: this began life as a "Quick Takes" comment, but it got pretty long, so I figured I might as well convert it to a regular post.] In LM training , every token provides new information about "the world beyond the LM" that can be used/"learned" in-context to better predict future tokens in the same window. But when text is produced by autoregressive sampling from the same LM, it is not informative in th
Explore this link on the map →related reading
- Modifying LLM Beliefs with Synthetic Document Finetuningalignment.anthropic.com
- GenAI Handbookgenai-handbook.github.io
- RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- [2203.02155] Training language models to follow instructions with human feedbackarxiv.org
- How do LLMs generalize when we do training that is intuitively compatible with two off-distribution behaviors? — LessWronglesswrong.com
- Large Language Diffusion Modelsarxiv.org
- Self-Adapting Language Modelsarxiv.org
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
- Unfamiliar Finetuning Examples Control How Language Models Hallucinatearxiv.org
- [2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org
- When "technically true" becomes "actually misleading"theargumentmag.com