About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Kush Bhatia
- sl:arxiv_num : 2306.07536
- sl:arxiv_published : 2023-06-13T04:37:00Z
- sl:arxiv_summary : Large language models (LLMs) exhibit in-context learning abilities which
enable the same model to perform several tasks without any task-specific
training. In contrast, traditional adaptation approaches, such as fine-tuning,
modify the underlying models for each specific task. In-context learning,
however, consistently underperforms task-specific tuning approaches even when
presented with the same examples. While most existing approaches (e.g., prompt
engineering) focus on the LLM's learned representations to patch this
performance gap, our analysis actually reveal that LLM representations contain
sufficient information to make good predictions. As such, we focus on the LLM's
reasoning abilities and demonstrate that this performance gap exists due to
their inability to perform simple probabilistic reasoning tasks. This raises an
intriguing question: Are LLMs actually capable of learning how to reason in a
task-agnostic manner? We answer this in the affirmative and propose TART which
generically improves an LLM's reasoning abilities using a synthetically trained
Transformer-based reasoning module. TART trains this reasoning module in a
task-agnostic manner using only synthetic logistic regression tasks and
composes it with an arbitrary real-world pre-trained model without any
additional training. With a single inference module, TART improves performance
across different model families (GPT-Neo, Pythia, BLOOM), model sizes (100M -
6B), tasks (14 NLP binary classification tasks), and even across different
modalities (audio and vision). Additionally, on the RAFT Benchmark, TART
improves GPT-Neo (125M)'s performance such that it outperforms BLOOM (176B),
and is within 4% of GPT-3 (175B). Our code and models are available at
https://github.com/HazyResearch/TART .@en
- sl:arxiv_title : TART: A plug-and-play Transformer module for task-agnostic reasoning@en
- sl:arxiv_updated : 2023-06-13T04:37:00Z
- sl:bookmarkOf : https://arxiv.org/abs/2306.07536
- sl:creationDate : 2023-06-15
- sl:creationTime : 2023-06-15T07:44:01Z
Documents with similar tags (experimental)