Paper

Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization

Unreadunread

AI summary

arXiv:2606. 23989v1 Announce Type: new Abstract: End-to-end large language models (LLMs) produce fluent multi-document summaries but remain prone to hallucination, and the attributions they offer are typically coarse (whole documents or passages) and generated post hoc, leaving each summary statement hard to verify.

Reading status

Priority

About this paper

Authors: Shuo Guan
Released: 2026-06-24 (15d ago)
Topic: Related to current project
Relation to my work: Read next because Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: strong, eval, source, token, line, rate, control, trained. Source: arxiv cs.CL (NLP).
arXiv: 2606.23989

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.