{"ID":2839818,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.14098","arxiv_id":"2511.14098","title":"Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Data","abstract":"In this paper, we model and analyze how a network of interacting LLMs performs collaborative question-answering (CQA) in order to estimate a ground truth given a distributed set of documents. This problem is interesting because LLMs often hallucinate when direct evidence to answer a question is lacking, and these effects become more pronounced in a network of interacting LLMs. The hallucination spreads, causing previously accurate LLMs to hallucinate. We study interacting LLMs and their hallucination by combining novel ideas of mean-field dynamics (MFD) from network science and the randomized utility model from economics to construct a useful generative model. We model the LLM with a latent state that indicates if it is truthful or not with respect to the ground truth, and extend a tractable analytical model considering an MFD to model the diffusion of information in a directed network of LLMs. To specify the probabilities that govern the dynamics of the MFD, we propose a randomized utility model. For a network of LLMs, where each LLM has two possible latent states, we posit sufficient conditions for the existence and uniqueness of a fixed point and analyze the behavior of the fixed point in terms of the incentive (e.g., test-time compute) given to individual LLMs. We experimentally study and analyze the behavior of a network of $100$ open-source LLMs with respect to data heterogeneity, node capability, network structure, and sensitivity to framing on multiple semi-synthetic datasets.","short_abstract":"In this paper, we model and analyze how a network of interacting LLMs performs collaborative question-answering (CQA) in order to estimate a ground truth given a distributed set of documents. This problem is interesting because LLMs often hallucinate when direct evidence to answer a question is lacking, and these effec...","url_abs":"https://arxiv.org/abs/2511.14098","url_pdf":"https://arxiv.org/pdf/2511.14098v1","authors":"[\"Adit Jain\",\"Vikram Krishnamurthy\",\"Yiming Zhang\"]","published":"2025-11-18T03:32:17Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.MA\",\"cs.SI\",\"eess.SY\"]","methods":"[\"Diffusion Model\",\"Large Language Model\"]","has_code":false}