Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

[R] System 2 Attention (is something you might need too) (alien.top)

submitted 11 months ago by APaperADay@alien.top to c/machinelearning@academy.garden

4 comments fedilink hide all child comments

Paper: https://arxiv.org/abs/2311.11829

Abstract:

Soft attention in Transformer-based Large Language Models (LLMs) is susceptible to incorporating irrelevant information from the context into its latent representations, which adversely affects next token generations. To help rectify these issues, we introduce System 2 Attention (S2A), which leverages the ability of LLMs to reason in natural language and follow instructions in order to decide what to attend to. S2A regenerates the input context to only include the relevant portions, before attending to the regenerated context to elicit the final response. In experiments, S2A outperforms standard attention-based LLMs on three tasks containing opinion or irrelevant information, QA, math word problems and longform generation, where S2A increases factuality and objectivity, and decreases sycophancy.

you are viewing a single comment's thread
view the rest of the comments

[–] reverendCappuccino@alien.top 1 points 11 months ago

Well, it's more like a psychological term, and attention is already there to illustrate the intended meaning of a dot product. The analogy holds up, so why doubting the validity of using system 2 attention rather than that of using attention at all?