DeepAI AI Chat
Log In Sign Up

Unlocking Temporal Question Answering for Large Language Models Using Code Execution

by   Xingxuan Li, et al.
National University of Singapore
Alibaba Group
Nanyang Technological University

Large language models (LLMs) have made significant progress in natural language processing (NLP), and are utilized extensively in various applications. Recent works, such as chain-of-thought (CoT), have shown that intermediate reasoning steps can improve the performance of LLMs for complex reasoning tasks, such as math problems and symbolic question-answering tasks. However, we notice the challenge that LLMs face when it comes to temporal reasoning. Our preliminary experiments show that generating intermediate reasoning steps does not always boost the performance of complex temporal question-answering tasks. Therefore, we propose a novel framework that combines the extraction capability of LLMs and the logical reasoning capability of a Python solver to tackle this issue. Extensive experiments and analysis demonstrate the effectiveness of our framework in handling intricate time-bound reasoning tasks.


page 1

page 2

page 3

page 4


Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Models

Large language models (LLMs) have scaled up to unlock a wide range of co...

Rethinking with Retrieval: Faithful Large Language Model Inference

Despite the success of large language models (LLMs) in various natural l...

RET-LLM: Towards a General Read-Write Memory for Large Language Models

Large language models (LLMs) have significantly advanced the field of na...

Rationale-Augmented Ensembles in Language Models

Recent research has shown that rationales, or step-by-step chains of tho...

Exploring the Integration Strategies of Retriever and Large Language Models

The integration of retrieved passages and large language models (LLMs), ...

ThoughtSource: A central hub for large language model reasoning data

Large language models (LLMs) such as GPT-3 and ChatGPT have recently dem...

Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework

As large language models (LLMs) have become the norm in NLP, demonstrati...