Timezone: »

Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models’ Reasoning Performance
Yao Fu · Litu Ou · Yuhao Wan · Mingyu Chen · Hao Peng · Tushar Khot
Event URL: https://openreview.net/forum?id=iHwy0EcGB8 »

As large language models (LLMs) are continuously being developed, their evaluation becomes increasingly important yet challenging. This work proposes Chain-of-Thought Hub, an open-source evaluation suite on the multi-step reasoning capabilities of large language models. We are interested in this setting for two reasons:(1) from the behavior of GPT and PaLM model family, we observe that complex reasoning is likely to be a key differentiator between weaker and stronger LLMs;(2) we envisage large language models to become the next-generation computational platform and foster an ecosystem of LLM-based new applications, this naturally requires the foundation models to perform complex tasks that often involve the composition of linguistic and logical operations. Our approach is to compile a suite of challenging reasoning benchmarks to track the progress of LLMs. Our current results show that: (1) model scale clearly correlates with reasoning capabilities;(2) As of May 2023, Claude-v1.3 and PaLM-2 are the only two models that are comparable with GPT-4, while open-sourced models still lag behind;(3) LLaMA-65B performs closely to code-davinci-002, indicating that with successful further development such as reinforcement learning from human feedback (RLHF), it has great potential to be close to GPT-3.5-Turbo. Our results also suggest that for the open-source efforts to catch up, the community may focus more on building better base models and exploring RLHF.

Author Information

Yao Fu (University of Edinburgh)
Litu Ou (University of Edinburgh)

Year 3 student in UoE.

Yuhao Wan (University of Washington)
Mingyu Chen (University of Edinburgh)
Hao Peng (Allen Institute for Artificial Intelligence)
Tushar Khot (Allen Institute for AI)

More from the Same Authors