Metraipolis › archive › dc_26db4eb4d985
VALCON: Benchmarking and Enhancing Value Consistency in Large Language Models via Dual-Role Variation — arXiv:2610.21304
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21304
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:55:59.365Z
- SHA-256 of the archived text
1789c24797d62db629bfca22a6bce34af5e614b42a096dbe1d78218c884c81f8- Stable URL of this page
https://metraipolis.com/documento/dc_26db4eb4d985
How to cite
VALCON: Benchmarking and Enhancing Value Consistency in Large Language Models via Dual-Role Variation — arXiv:2610.21304 — arXiv (en), https://arxiv.org/abs/2610.21304 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_26db4eb4d985 (Metraipolis archive dc_26db4eb4d985, sha256 1789c24797d62db629bfca22a6bce34af5e614b42a096dbe1d78218c884c81f8)
BibTeX
@misc{dc26db4eb4d985,
title = {VALCON: Benchmarking and Enhancing Value Consistency in Large Language Models via Dual-Role Variation — arXiv:2610.21304},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21304},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_26db4eb4d985; sha256 1789c24797d62db629bfca22a6bce34af5e614b42a096dbe1d78218c884c81f8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21304. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Current value alignment evaluations for large language models (LLMs) heavily rely on output compliance, overlooking whether LLMs maintain value consistency when alternating between generator and evaluator roles. Such consistency is increasingly important because modern LLM agents and alignment pipelines often rely on the same LLM to both generate actions and evaluate their acceptability. To mitigate this limitation, we propose VALCON, a role-driven data construction framework that operationalizes value consistency into three benchmark suites (VAB-Consistency, VAB-Boundary, VAB-Challenge) via dual-role variation. By systematically pairing an LLM's generative behavior with its evaluative judgments under identical principles, VALCON synthesizes target evaluation data that exposes hidden value discrepancies. Experiments on 28 LLMs reveal pervasive cross-role inconsistency: models with highly compliant outputs frequently fail to align their judgments with their own generations. To understand and address this gap, we perform mechanistic probing that uncovers a role-dependent representational decoupling associated with this behavioral asymmetry. Guided by these insights, we propose a representation-directed intervention that effectively mitigates consistency failures. Our work establishes value consistency as a distinct alignment dimension and provides a complete evaluation-analysis-mitigation pipeline. Code and data are available at this https URL . 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/2610.21304 — 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 2026-10-16T08:44:47.637Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).