Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an approach works very well for tasks that only require forward reasoning (e.g., straightforward arithmetic), it is less effective for constraint solving tasks that require more sophisticated planning and search. In this paper, we propose a new satisfiability-aided language modeling approach for improving the reasoning capabilities of LLMs. We use an LLM to generate a declarative task specification rather than an imperative program and leverage an off-the-shelf automated theorem prover to derive the final answer. This approach has two key advantages. The declarative specification is closer to the problem description than the reasoning steps are, so the LLM can parse it more accurately. Furthermore, by offloading the actual reasoning task to an automated theorem prover, our approach can guarantee the correctness of the answer with respect to the parsed specification and avoid planning errors in the reasoning process. We evaluate SATLM on 6 different datasets and show that it consistently outperforms program-aided LMs in an imperative paradigm (PROGLM). In particular, SATLM outperforms PROGLM by 23% on a challenging subset of GSM; SATLM also achieves a new SoTA on LSAT, surpassing previous models that are trained on the full training set.

翻译：暂无翻译