SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.14312 · 2024

ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
rucaibox/chainlm canonical 4 of 10
FunctionStatusWhere it lives
get_input Ran rucaibox/chainlm/debate/debate4cot.py
pointer only (licence: NONE) · get_code("9fecbd5be33d8972")
get_res_batch Ran rucaibox/chainlm/generate/complicate_filter.py
pointer only (licence: NONE) · get_code("ee1261cc031b3ee4")
get_res_batch Ran rucaibox/chainlm/generate/generate_cot.py
pointer only (licence: NONE) · get_code("41f2fda3501db450")
get_res_batch Ran rucaibox/chainlm/generate/specify_filter.py
pointer only (licence: NONE) · get_code("5ddeec251ac6468c")
annotate Not yet run rucaibox/chainlm/generate/filter_claude.py
pointer only (licence: NONE) · get_code("2cf2868f64341a27")
get_res_batch Not yet run rucaibox/chainlm/generate/diversify_filter.py
pointer only (licence: NONE) · get_code("12f7e3d5087fec14")
get_res_batch Not yet run rucaibox/chainlm/generate/filter_chatgpt.py
pointer only (licence: NONE) · get_code("cce269798b70d493")
get_res_batch Not yet run rucaibox/chainlm/generate/generate_question.py
pointer only (licence: NONE) · get_code("3ac1b552c4ac7840")
get_res_batch Not yet run rucaibox/chainlm/generate/rewrite_cot.py
pointer only (licence: NONE) · get_code("0d18ca984c151622")
load_model Not yet run rucaibox/chainlm/debate/debate4cot.py
pointer only (licence: NONE) · get_code("5872a9172aa4cf7b")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Chain-of-Thought (CoT) prompting can enhance the reasoning capabilities of large language models (LLMs), establishing itself as a primary approach to solving complex reasoning tasks. Existing CoT synthesis approaches usually focus on simpler reasoning tasks and thus result in low-quality and inconsistent CoT prompts. In response to this challenge, we present an empirical investigation of CoT prompting and introduce CoTGenius, a novel framework designed for the automatic generation of superior CoT prompts. CoTGenius is developed based on three major evolution strategies, i.e., complicate, diversify, and specify-alongside two filtering mechanisms: evolutionary success judgement and correctness verification. We further employ CoTGenius to create an extensive CoT dataset, and subsequently fine-tune the Llama 2-Chat 7B and 13B models on this dataset. We call the resulting model ChainLM. To deal with the cumulative error issue in reasoning steps, we propose a step-level debating method, wherein multiple debaters discuss each reasoning step to arrive at the correct answer. Extensive experiments demonstrate that our ChainLM models exhibit enhanced proficiency in addressing a spectrum of complex reasoning problems compared to existing models. In addition, we conduct an in-depth analysis of the impact of data categories within CoTGenius on the model performance. We release our dataset and code at https://github.com/RUCAIBox/ChainLM.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.14312")
get_code_for_paper("2403.14312")
have("2403.14312")

Connect an agent — have() is free.