Metraipolis › archive › dc_88aa45fa4463
CLUE: Uncovering Social Context for Pragmatic Understanding — arXiv:2610.22167
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22167
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:02:02.629Z
- SHA-256 of the archived text
5c9b55181b00fa919276b04a8292a767bc94dc163ce273725f0e1d447bc75da3- Stable URL of this page
https://metraipolis.com/documento/dc_88aa45fa4463
How to cite
CLUE: Uncovering Social Context for Pragmatic Understanding — arXiv:2610.22167 — arXiv (en), https://arxiv.org/abs/2610.22167 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_88aa45fa4463 (Metraipolis archive dc_88aa45fa4463, sha256 5c9b55181b00fa919276b04a8292a767bc94dc163ce273725f0e1d447bc75da3)
BibTeX
@misc{dc88aa45fa4463,
title = {CLUE: Uncovering Social Context for Pragmatic Understanding — arXiv:2610.22167},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22167},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_88aa45fa4463; sha256 5c9b55181b00fa919276b04a8292a767bc94dc163ce273725f0e1d447bc75da3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22167. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Understanding a conversation requires connecting what is said to the speakers' relationships, expectations, and earlier exchanges. Prior work shows that supplying relevant context can improve models' social judgments, but much of this information may already be present in the conversation. This motivates training models to discover the cues that matter and use them to support an interpretation. We propose CLUE, a two-stage training pipeline that combines supervised evidence reasoning with GRPO guided by Grounded Information Utilization ($\mathrm{IU}_{\mathrm{G}}$). This reward credits new, evidence-supported social inferences while accounting for reasoning effort. We train on a small set of conversational examples to assess effectiveness and generalization across tasks, languages, and genres. At inference time, the trained model reasons over the supplied interaction in a self-contained manner. Compared with base Qwen, CLUE achieves relative gains of 17.3% in-domain and 9.3% out-of-domain in average weighted F1, with higher F1 on four of five out-of-domain evaluations. These gains are accompanied by over 80% fewer reasoning tokens on average in both domains. Human evaluation further finds that CLUE more often grounds its explanations in specific conversational content, with closer alignment between its quoted evidence and human-selected context.
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/2610.22167 — 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 2026-10-16T08:44:47.697Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).