Metraipolis › archive › dc_ec8f22e486a6

Collective Bias Mitigation via Model Routing and Collaboration — arXiv:2610.03240

Source
arXiv
Original
https://arxiv.org/abs/2610.03240
License (as archived)
CC0-1.0
Archived
2026-10-05T22:51:46.177Z
SHA-256 of the archived text
79056c6732cd6a8f8d126c8b518c6847f42a65e27c1d43f0a39696a4af5fd7ec
Stable URL of this page
https://metraipolis.com/documento/dc_ec8f22e486a6

How to cite

Collective Bias Mitigation via Model Routing and Collaboration — arXiv:2610.03240 — arXiv, https://arxiv.org/abs/2610.03240 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec8f22e486a6 (Metraipolis archive dc_ec8f22e486a6, sha256 79056c6732cd6a8f8d126c8b518c6847f42a65e27c1d43f0a39696a4af5fd7ec)
BibTeX
@misc{dcec8f22e486a6,
  title = {Collective Bias Mitigation via Model Routing and Collaboration — arXiv:2610.03240},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03240},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec8f22e486a6; sha256 79056c6732cd6a8f8d126c8b518c6847f42a65e27c1d43f0a39696a4af5fd7ec},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03240. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly deployed in public health, finance, and governance, requiring both accuracy and societal value alignment. Despite recent advances, LLMs often perpetuate or amplify bias embedded in their training data, posing challenges to fairness. While self-debiasing encourages an LLM to identify and correct its own biases, relying on a single model's intrinsic knowledge may be insufficient to address deeply ingrained stereotypes. To address this limitation, we introduce Collective Bias Mitigation (CBM), a framework that alleviates bias by learning fine-grained model behavior and fostering knowledge sharing among diverse LLMs. This work is the first to systematically explore the effective selection and organization of distinct LLMs to cultivate fairer LLM responses. Experiments show CBM substantially outperforms standalone baselines (e.g., in the top-7 setting, Committee lowers the age bias score from 0.25 to 0.10). Our Debating and Committee topologies achieve substantial bias reduction, with the latter balancing mitigation effectiveness and inference cost, highlighting the potential of CBM for fairer LLMs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.03240 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T22:46:10.582Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).