Papers › In-Context Learning Creates Task Vectors

In-Context Learning Creates Task Vectors

24 Oct 2023arXiv:2310.15916archive 2025-07-28

Roee Hendel, Mor Geva, Amir Globerson

In-context learning (ICL) in Large Language Models (LLMs) has emerged as a powerful new learning paradigm. However, its underlying mechanism is still not well understood. In particular, it is challenging to map it to the "standard" machine learning framework, where one uses a training set S to find a best-fitting function f(x) in some hypothesis class. Here we make progress on this problem by showing that the functions learned by ICL often have a very simple structure: they correspond to the transformer LLM whose only inputs are the query x and a single "task vector" calculated from the training set. Thus, ICL can be seen as compressing S into a single task vector θ(S) and then using this task vector to modulate the transformer to produce the output. We support the above claim via comprehensive experiments across a range of models and tasks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

roeehendel/icl_task_vectors officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

In-Context Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections