Metraipolis › archive › dc_d9d0806a71d3

EVAR: Evidence-Validated Hypothesis Admission for Budget-Aware Narrative Reasoning — arXiv:2608.29835

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29835
License (as archived)
CC0-1.0
Archived
2026-10-17T08:07:10.739Z
SHA-256 of the archived text
4c701660142ca3c66a449c5f4102f522442ef2c89874c89954b0d5564be38ced
Stable URL of this page
https://metraipolis.com/documento/dc_d9d0806a71d3

How to cite

EVAR: Evidence-Validated Hypothesis Admission for Budget-Aware Narrative Reasoning — arXiv:2608.29835 — arXiv (en), https://arxiv.org/abs/2608.29835 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d9d0806a71d3 (Metraipolis archive dc_d9d0806a71d3, sha256 4c701660142ca3c66a449c5f4102f522442ef2c89874c89954b0d5564be38ced)
BibTeX
@misc{dcd9d0806a71d3,
  title = {EVAR: Evidence-Validated Hypothesis Admission for Budget-Aware Narrative Reasoning — arXiv:2608.29835},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29835},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d9d0806a71d3; sha256 4c701660142ca3c66a449c5f4102f522442ef2c89874c89954b0d5564be38ced},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29835. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central failure mode is that unsupported intermediate hypotheses can enter the reasoning trajectory and contaminate subsequent inference, especially when evidence is scattered across distant parts of the story. To address this problem, we propose EVAR, an evidence-validated hypothesis admission framework for budget-aware narrative reasoning. EVAR first compiles the narrative into an immutable evidence store of source-linked atomic claims and assigns an instance-specific inference budget from unresolved gaps and uncertainty signals. During refinement, EVAR directly proposes candidate hypotheses for unresolved gaps, constructs hypothesis-conditioned validation challenges, and verifies each candidate against the locked store before admission: supported hypotheses enter the answer-supporting state, unverifiable ones are quarantined, and contradictory ones are discarded. A sufficiency-based stopping mechanism further avoids unnecessary refinement. Experiments on NarraCrime and multiple public reasoning benchmarks show that EVAR improves both task performance and evidence faithfulness while maintaining controllable inference cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.29835 — 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 2026-10-17T07:47:52.739Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).