Newest and Highest Rated Papers
Advanced filtersTopic: AllExperimental
Topic
Topics are auto-detected from title, abstract, and metadata and may be imperfect.
Bayesian scaling laws for in-context learning
Aryaman Arora, Dan Jurafsky, Christopher Potts, Noah D. Goodman
arXiv·2024
In-context learning (ICL) is a powerful technique for getting language models to perform complex tasks with no training updates. Prior work has established strong correlations between the number of in-context examples provided and the accuracy of the model's predictions. In this paper, we seek to explain this correlation by showing that ICL approximates a Bayesian learner. This perspective gives rise to a novel Bayesian scaling law for ICL. In experiments with \mbox{GPT-2} models of different sizes, our scaling law matches existing scaling laws in accuracy while also offering interpretable terms for task priors, learning efficiency, and per-example probabilities. To illustrate the analytic power that such interpretable scaling laws provide, we report on controlled synthetic dataset experiments designed to inform real-world studies of safety alignment. In our experimental protocol, we use SFT or DPO to suppress an unwanted existing model capability and then use ICL to try to bring that capability back (many-shot jailbreaking). We then study ICL on real-world instruction-tuned LLMs using capabilities benchmarks as well as a new many-shot jailbreaking dataset. In all cases, Bayesian scaling laws accurately predict the conditions under which ICL will cause suppressed behaviors to reemerge, which sheds light on the ineffectiveness of post-training at increasing LLM safety.
No ratings yet
View paper →Mapping the Mind of a Large Language Model
Anthropic
Anthropic Blog·2024
We have identified how millions of concepts are represented inside Claude Sonnet, one of our deployed large language models. This is the first ever detailed look inside a modern, production-grade large language model.
No ratings yet
View paper →Emergent introspective awareness in large language models
Anthropic
Anthropic Blog·2025
Research from Anthropic on the ability of large language models to introspect
No ratings yet
View paper →Let’s talk about AIDS, baby! Critiquing the HIV and AIDS Act, 2017 in India through a reproductive justice framework - PMC
Apoorva Nangia, Jwalika Balaji
pmc.ncbi.nlm.nih.gov
The HIV and AIDS Act was enacted in India in 2017 to protect the right to privacy, bodily autonomy, and non-discrimination of Persons Living with HIV (PLHIV). Prior to the Act, HIV/AIDS-related jurisprudence in India developed largely through ...
No ratings yet
View paper →