@inproceedings{verma-etal-2026-selene,
    title = "{SELENE}: Selective and Evidence-Weighted {LLM} Debating for Efficient and Reliable Reasoning",
    author = "Verma, Akshay  and
      Gupta, Swapnil  and
      Gupta, Deepak  and
      Sircar, Prateek  and
      Pillai, Siddharth",
    editor = {Matusevych, Yevgen  and
      Eryi{\u{g}}it, G{\"u}l{\c{s}}en  and
      Aletras, Nikolaos},
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-industry.7/",
    pages = "95--104",
    ISBN = "979-8-89176-384-5",
    abstract = "Multi-Agent Debate (MAD) frameworks improve factual reliability in large language models (LLMs) by allowing agents to critiqueand refine one another{'}s reasoning. Yet, existing MAD systems are computationally expensive and prone to degradation under pro-longed debates due to redundant exchanges and unstable judging. We propose a lightweight,industry-deployable alternative that unifies Selective Debate Initiation (SDI) with Evidence Weighted Self-Consistency (EWSC) for adaptive, debate-on-demand reasoning. SDI dynamically predicts when debate is necessary by detecting confidence-likelihood misalignment and semantic disagreement, skippingwell-aligned queries to conserve computation. EWSC replaces a single-judge verdict with a variance-aware, evidence-weighted aggregation across paraphrased evaluations, yielding more stable factual judgments. Combined, SDI and EWSC reduce token consumption by nearly 50{\%} while improving both accuracy and calibration. Evaluated on BoolQ, CosmosQA, and an internal QnA benchmark, our framework achieves higher factual robustness and efficiency, demonstrating that scalable, epistemically reliable multi-agent reasoning is practical for real-world LLM deployments."
}