{"paper":{"title":"Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Author revisions act as signals to improve LLM-generated responses to peer reviews","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Qian Ruan","submitted_at":"2026-01-19T14:07:10Z","abstract_excerpt":"Author response (rebuttal) writing is a critical stage of scientific peer review that demands substantial author effort. In practice, authors possess domain expertise, author-only information, and response strategies - concrete forms of author expertise and intent - and seek NLP assistance that integrates these signals into author response generation (ARG). Yet this author-in-the-loop paradigm lacks formal NLP formulation and systematic study: no dataset provides fine-grained author signals, existing ARG work lacks author inputs and controls, and no evaluation measures response reflection of a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments with SOTA LLMs demonstrate the benefits of author input and evaluation-guided refinement, the impact of input specificity on response quality, and controllability-quality trade-offs.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That paper revisions serve as reliable proxies for author signals and that the collected triplets capture genuine author expertise and intent without systematic bias from revision practices.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Introduces Re3Align dataset of review-response-revision triplets, REspGen author-in-the-loop generation framework, and REspEval multi-metric suite for controllable peer-review response generation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Author revisions act as signals to improve LLM-generated responses to peer reviews","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bcc015ee8450582cc578b48b28cc3df25a2b6a1e4efe9b29dd65cc2f5e560c80"},"source":{"id":"2602.11173","kind":"arxiv","version":3},"verdict":{"id":"b448b29b-c1ed-4ba2-9d23-80236a754416","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T13:02:41.375119Z","strongest_claim":"Experiments with SOTA LLMs demonstrate the benefits of author input and evaluation-guided refinement, the impact of input specificity on response quality, and controllability-quality trade-offs.","one_line_summary":"Introduces Re3Align dataset of review-response-revision triplets, REspGen author-in-the-loop generation framework, and REspEval multi-metric suite for controllable peer-review response generation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That paper revisions serve as reliable proxies for author signals and that the collected triplets capture genuine author expertise and intent without systematic bias from revision practices.","pith_extraction_headline":"Author revisions act as signals to improve LLM-generated responses to peer reviews"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.11173/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}