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 o...
Enhancing the zero-shot performance of instruction-following models requires heavy computation, eith...
Large Language Models (LLMs) have demonstrated impressive zero shot performance on a wide range of N...
Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performanc...
Pretrained large language models (LLMs) are widely used in many sub-fields of natural language proce...
Chain-of-Thought (CoT) is a technique that guides Large Language Models (LLMs) to decompose complex ...
This paper show a work on better use of LLMs with SelfzCoT a self-prompt zero-shot CoT. Specifically...
We present a new method LiST is short for Lite Prompted Self-Training for parameter-efficient fine-t...
Deploying large language models (LLMs) is challenging because they are memory inefficient and comput...
Large language models (LMs) beyond a certain scale, demonstrate the emergent capability of generatin...
Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unsee...
In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension a...
Emergent chain-of-thought (CoT) reasoning capabilities promise to improve performance and explainabi...
Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning step...
Large language models that are capable of zero or few-shot prompting approaches have given rise to t...
Pretrained large language models (LLMs) are strong in-context learners that are able to perform few-...
Enhancing the zero-shot performance of instruction-following models requires heavy computation, eith...
Large Language Models (LLMs) have demonstrated impressive zero shot performance on a wide range of N...
Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performanc...
Pretrained large language models (LLMs) are widely used in many sub-fields of natural language proce...
Chain-of-Thought (CoT) is a technique that guides Large Language Models (LLMs) to decompose complex ...
This paper show a work on better use of LLMs with SelfzCoT a self-prompt zero-shot CoT. Specifically...
We present a new method LiST is short for Lite Prompted Self-Training for parameter-efficient fine-t...
Deploying large language models (LLMs) is challenging because they are memory inefficient and comput...
Large language models (LMs) beyond a certain scale, demonstrate the emergent capability of generatin...
Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unsee...
In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension a...
Emergent chain-of-thought (CoT) reasoning capabilities promise to improve performance and explainabi...
Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning step...
Large language models that are capable of zero or few-shot prompting approaches have given rise to t...
Pretrained large language models (LLMs) are strong in-context learners that are able to perform few-...
Enhancing the zero-shot performance of instruction-following models requires heavy computation, eith...
Large Language Models (LLMs) have demonstrated impressive zero shot performance on a wide range of N...
Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performanc...