@inproceedings{arakelyan-etal-2025-flare,
    title = "{FLARE}: Faithful Logic-Aided Reasoning and Exploration",
    author = "Arakelyan, Erik  and
      Minervini, Pasquale  and
      Lewis, Patrick  and
      Verga, Pat  and
      Augenstein, Isabelle",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1193/",
    pages = "23396--23414",
    ISBN = "979-8-89176-332-6",
    abstract = "Modern Question Answering (QA) and Reasoning approaches with Large Language Models (LLMs) commonly use Chain-of-Thought (CoT) prompting but struggle with generating outputs faithful to their intermediate reasoning chains. While neuro-symbolic methods like Faithful CoT (F-CoT) offer higher faithfulness through external solvers, they require code-specialized models and struggle with ambiguous tasks.We introduce $\textbf{F}$aithful $\textbf{L}$ogic-$\textbf{A}$ided $\textbf{R}$easoning and $\textbf{E}$xploration ($\textbf{FLARE}$), which uses LLMs to plan solutions, formalize queries into logic programs, and simulate code execution through multi-hop search without external solvers. Our method achieves SOTA results on $\mathbf{7}$ out of $\mathbf{9}$ diverse reasoning benchmarks and 3 out of 3 logic inference benchmarks while enabling measurement of reasoning faithfulness. We demonstrate that model faithfulness correlates with performance and that successful reasoning traces show an 18.1{\%} increase in unique emergent facts, 8.6{\%} higher overlap between code-defined and execution-trace relations, and 3.6{\%} reduction in unused relations."
}