Metraipolis › archive › dc_c65d5941be75
Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue — arXiv:2609.19155
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19155
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:47:57.422Z
- SHA-256 of the archived text
65741596d827a5a1bee5eb94d34052c16ed4cf5c7917acbb7743cf85ed248475- Stable URL of this page
https://metraipolis.com/documento/dc_c65d5941be75
How to cite
Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue — arXiv:2609.19155 — arXiv (en), https://arxiv.org/abs/2609.19155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c65d5941be75 (Metraipolis archive dc_c65d5941be75, sha256 65741596d827a5a1bee5eb94d34052c16ed4cf5c7917acbb7743cf85ed248475)
BibTeX
@misc{dcc65d5941be75,
title = {Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue — arXiv:2609.19155},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19155},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c65d5941be75; sha256 65741596d827a5a1bee5eb94d34052c16ed4cf5c7917acbb7743cf85ed248475},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In Human-LLM dialogue, follow-up user utterances may implicitly conflict with earlier intents, leading the LLM to misinterpret user needs and generate inappropriate responses. A reliable dialogue system should proactively detect user-side conflicts before generating a response and seek clarification when necessary. However, prior work has largely focused on LLM-side conflicts, leaving user-side conflicts underexplored. To fill this gap, we construct UC-Bench, a human-annotated benchmark for evaluating user-side conflict detection. Preliminary experiments show that existing LLMs struggle with this task, especially when conflicts arise from implicit incompatibilities grounded in dialogue history. To improve lightweight LLMs with limited training data, we investigate data synthesis for user-side conflict detection. Existing synthesis methods do not explicitly model the implicit incompatibilities between historical and current user utterances, making it difficult to capture the evolution of conflicts and to generate reliably labeled implicit conflict samples. We propose SynUC, a constraint-guided synthesis method that represents user-side conflicts in a constraint space and uses the SPEAKING framework to guide traceable constraint transformations. Applying SynUC to WildChat, we construct UC-Data, a user-side conflict training set containing 2,487 samples. On UC-Bench, Qwen3.5-4B trained on UC-Data outperforms larger general-purpose LLMs such as Claude Opus 4.8, as well as the same backbone trained on data synthesized by existing methods. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.19155 — 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 2026-10-10T03:24:08.111Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).