The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:IFFK623Lrecord.jsonopen to challenge →
read the original abstract
Language models (LMs) with less than 100B parameters are known to perform poorly on chain-of-thought (CoT) reasoning in contrast to large LMs when solving unseen tasks. In this work, we aim to equip smaller LMs with the step-by-step reasoning capability by instruction tuning with CoT rationales. In order to achieve this goal, we first introduce a new instruction-tuning dataset called the CoT Collection, which augments the existing Flan Collection (including only 9 CoT tasks) with additional 1.84 million rationales across 1,060 tasks. We show that CoT fine-tuning Flan-T5 (3B & 11B) with CoT Collection enables smaller LMs to have better CoT capabilities on unseen tasks. On the BIG-Bench-Hard (BBH) benchmark, we report an average improvement of +4.34% (Flan-T5 3B) and +2.60% (Flan-T5 11B), in terms of zero-shot task accuracy. Furthermore, we show that instruction tuning with CoT Collection allows LMs to possess stronger few-shot learning capabilities on 4 domain-specific tasks, resulting in an improvement of +2.24% (Flan-T5 3B) and +2.37% (Flan-T5 11B), even outperforming ChatGPT utilizing demonstrations until the max length by a +13.98% margin. Our code, the CoT Collection data, and model checkpoints are publicly available.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse
AdapShot adaptively tunes shot count via entropy probes and reuses semantically-matched KV caches with position decoupling to deliver ~10% accuracy gains and 4.64x speedup over fixed-shot baselines.
-
AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse
AdapShot adaptively optimizes shot counts via probe entropy and semantic KV cache reuse with decoupling, reporting ~10% gain and 4.64x speedup over DBSA.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
-
LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance
LicenseGPT fine-tuned on 500 expert-annotated licenses raises prediction agreement to 64.30% and cuts per-license analysis time by 94.44% from 108s to 6s in lawyer user studies.
-
MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
MetaEvo is a two-stage framework using preference optimization for principle abstraction followed by modular reuse to enable continual improvement of LLM agents on reasoning tasks.
-
Retrieval-Augmented Generation for Large Language Models: A Survey
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
-
A Comprehensive Overview of Large Language Models
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.