Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision

Large language models (LLMs) have shown promising performance in mathematical and logical reasoning benchmarks. However, recent studies have pointed to memorization, rather than generalization, as one of the leading causes for such performance. LLMs, in fact, are susceptible to content variations, demonstrating a lack of robust symbolic abstractions supporting their reasoning process. To improve reliability, many attempts have been made to combine LLMs with symbolic methods. Nevertheless, existing approaches fail to effectively leverage symbolic representations due to the challenges involved in developing reliable and scalable verification mechanisms. In this paper, we propose to overcome such limitations by generating symbolic reasoning trajectories and select the high-quality ones using a process reward model automatically tuned based on Monte Carlo estimation. The trajectories are then employed via fine-tuning methods to improve logical reasoning and generalization. Our results on logical reasoning benchmarks such as FOLIO and LogicAsker show the effectiveness of the proposed method with large gains on frontier and open-weight models. Moreover, additional experiments on claim verification reveal that fine-tuning on the generated symbolic reasoning trajectories enhances out-of-domain generalizability, suggesting the potential impact of symbolically-guided process supervision in alleviating the effect of memorization on LLM reasoning.

Temporal reasoning for timeline summarisation in social media

This paper explores whether enhancing temporal reasoning capabilities in Large Language Models (LLMs) can improve the quality of timeline summarization, the task of summarising long texts containing sequences of events, particularly social media threads . We introduce \textit{NarrativeReason}, a novel dataset focused on temporal relationships among sequential events within narratives, distinguishing it from existing temporal reasoning datasets that primarily address pair-wise event relationships. Our approach then combines temporal reasoning with timeline summarization through a knowledge distillation framework, where we first fine-tune a teacher model on temporal reasoning tasks and then distill this knowledge into a student model while simultaneously training it for the task of timeline summarization. Experimental results demonstrate that our model achieves superior performance on mental health-related timeline summarization tasks, which involve long social media threads with repetitions of events and a mix of emotions, highlighting the importance of leveraging temporal reasoning to improve timeline summarisation.