{"ID":2861169,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.03527","arxiv_id":"2510.03527","title":"Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs","abstract":"Language models can be sampled multiple times to access the distribution underlying their responses, but existing methods cannot efficiently synthesize rich epistemic signals across different long-form responses. We introduce Consensus Graphs (ConGrs), a flexible DAG-based data structure that represents shared information, as well as semantic variation in a set of sampled LM responses to the same prompt. We construct ConGrs using a light-weight lexical sequence alignment algorithm from bioinformatics, supplemented by the targeted usage of a secondary LM judge. Further, we design task-dependent decoding methods to synthesize a single, final response from our ConGr data structure. Our experiments show that synthesizing responses from ConGrs improves factual precision on two biography generation tasks by up to 31% over an average response and reduces reliance on LM judges by more than 80% compared to other methods. We also use ConGrs for three refusal-based tasks requiring abstention on unanswerable queries and find that abstention rate is increased by up to 56%. We apply our approach to the MATH and AIME reasoning tasks and find an improvement over self-verification and majority vote baselines by up to 6 points of accuracy. We show that ConGrs provide a flexible method for capturing variation in LM responses and using the epistemic signals provided by response variation to synthesize more effective responses.","short_abstract":"Language models can be sampled multiple times to access the distribution underlying their responses, but existing methods cannot efficiently synthesize rich epistemic signals across different long-form responses. We introduce Consensus Graphs (ConGrs), a flexible DAG-based data structure that represents shared informat...","url_abs":"https://arxiv.org/abs/2510.03527","url_pdf":"https://arxiv.org/pdf/2510.03527v1","authors":"[\"Sayan Ghosh\",\"Shahzaib Saqib Warraich\",\"Dhruv Tarsadiya\",\"Gregory Yauney\",\"Swabha Swayamdipta\"]","published":"2025-10-03T21:50:08Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}