{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/crispo-multi-aspect-critique-suggestion","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","arxiv_id":"2410.02748","date":"2024-10-03","proceeding":null,"authors":["Han He","Qianchu Liu","Lei Xu","Chaitanya Shivade","Yi Zhang","Sundararajan Srinivasan","Katrin Kirchhoff"],"abstract":"Existing automatic prompt engineering methods are typically designed for discriminative tasks, where new task prompts are iteratively refined with limited feedback from a single metric reflecting a single aspect. However, these approaches are suboptimal for generative tasks, which require more nuanced guidance beyond a single numeric metric to improve the prompt and optimize multiple aspects of the generated text. To address these challenges, we propose a novel multi-aspect Critique-Suggestion-guided automatic Prompt Optimization (CriSPO) approach. CriSPO introduces a critique-suggestion module as its core component. This module spontaneously discovers aspects, and compares generated and reference texts across these aspects, providing specific suggestions for prompt modification. These clear critiques and actionable suggestions guide a receptive optimizer module to make more substantial changes, exploring a broader and more effective search space. To further improve CriSPO with multi-metric optimization, we introduce an Automatic Suffix Tuning (AST) extension to enhance the performance of task prompts across multiple metrics. We evaluate CriSPO on 4 state-of-the-art LLMs across 4 summarization and 5 QA datasets. Extensive experiments show 3-4% ROUGE score improvement on summarization and substantial improvement of various metrics on QA. Code available at https://github.com/amazon-science/crispo","url_abs":"https://arxiv.org/abs/2410.02748v3","url_pdf":"https://arxiv.org/pdf/2410.02748v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"crispo-multi-aspect-critique-suggestion","repo_url":"https://github.com/amazon-science/crispo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/abstractive-text-summarization-on-cnn-daily","task":"Abstractive Text Summarization","dataset":"CNN / Daily Mail","model":"CriSPO 3-shot","rank_in_archive_order":52,"of":53,"metrics":{"ROUGE-L":"27.4"},"uses_additional_data":false},{"leaderboard":"/sota/abstractive-text-summarization-on-cnn-daily-2","task":"Abstractive Text Summarization","dataset":"CNN/Daily Mail","model":"CriSPO 3-shot","rank_in_archive_order":3,"of":4,"metrics":{"ROUGE-1":"42.1","ROUGE-2":"17"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-aci-bench","task":"Text Summarization","dataset":"ACI-Bench","model":"CriSPO 3-shot","rank_in_archive_order":1,"of":1,"metrics":{"ROUGE-1":"63.1","ROUGE-2":"32.5","ROUGE-L":"41"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-meetingbank","task":"Text Summarization","dataset":"MeetingBank","model":"CriSPO 3-shot","rank_in_archive_order":1,"of":2,"metrics":{"ROUGE-2":"46.5","ROUGE-L":"54.1","Rouge-1":"58.5"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-samsum-corpus","task":"Text Summarization","dataset":"SAMSum","model":"CriSPO 3-shot","rank_in_archive_order":9,"of":12,"metrics":{"ROUGE-1":"47.2","ROUGE-2":"20.8","ROUGE-L":"38.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.02748","atlas_url":"https://app.syntology.ai/?focus=2410.02748","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2410.02748"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.02748\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.02748"},"call":"get_concepts_for_paper(arxiv_id=\"2410.02748\")"}],"by_repo":[{"repo":"amazon-science/crispo","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a983c18dd1cf433b9612d4194188d5bc7b7c3d7ab1b1dea5d957ddcab0f12c1a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}