{"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/do-we-still-need-human-annotators-prompting","title":"Do we still need Human Annotators? Prompting Large Language Models for Aspect Sentiment Quad Prediction","arxiv_id":"2502.13044","date":"2025-02-18","proceeding":null,"authors":["Nils Constantin Hellwig","Jakob Fehle","Udo Kruschwitz","Christian Wolff"],"abstract":"Aspect sentiment quadruple prediction (ASQP) facilitates a detailed understanding of opinions expressed in a text by identifying the opinion term, aspect term, aspect category and sentiment polarity for each opinion. However, annotating a full set of training examples to fine-tune models for ASQP is a resource-intensive process. In this study, we explore the capabilities of large language models (LLMs) for zero- and few-shot learning on the ASQP task across five diverse datasets. We report F1 scores slightly below those obtained with state-of-the-art fine-tuned models but exceeding previously reported zero- and few-shot performance. In the 40-shot setting on the Rest16 restaurant domain dataset, LLMs achieved an F1 score of 52.46, compared to 60.39 by the best-performing fine-tuned method MVP. Additionally, we report the performance of LLMs in target aspect sentiment detection (TASD), where the F1 scores were also close to fine-tuned models, achieving 66.03 on Rest16 in the 40-shot setting, compared to 72.76 with MVP. While human annotators remain essential for achieving optimal performance, LLMs can reduce the need for extensive manual annotation in ASQP tasks.","url_abs":"https://arxiv.org/abs/2502.13044v1","url_pdf":"https://arxiv.org/pdf/2502.13044v1.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":"do-we-still-need-human-annotators-prompting","repo_url":"https://github.com/NilsHellwig/llm-prompting-asqp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/aspect-based-sentiment-analysis-absa-on-asqp","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"ASQP","model":"Gemma-3-27B (50-shot, self-consistency learning)","rank_in_archive_order":8,"of":12,"metrics":{"F1 (R15)":"41.74","F1 (R16)":"51.54"},"uses_additional_data":false},{"leaderboard":"/sota/aspect-based-sentiment-analysis-absa-on-asqp","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"ASQP","model":"Gemma-3-27B (10-shot, self-consistency learning)","rank_in_archive_order":9,"of":12,"metrics":{"F1 (R15)":"39.95","F1 (R16)":"46.23"},"uses_additional_data":false},{"leaderboard":"/sota/aspect-based-sentiment-analysis-absa-on-tasd","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"TASD","model":"Gemma-3-27B (50-shot, self-consistency learning)","rank_in_archive_order":6,"of":11,"metrics":{"F1 (R15)":"62.12","F1 (R16)":"68.53"},"uses_additional_data":false},{"leaderboard":"/sota/aspect-based-sentiment-analysis-absa-on-tasd","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"TASD","model":"Gemma-3-27B (10-shot, self-consistency learning)","rank_in_archive_order":9,"of":11,"metrics":{"F1 (R15)":"54.37","F1 (R16)":"66.75"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"NilsHellwig/llm-prompting-asqp","kind":"listed","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":"a5617d37a7c830224227a38d9bdfe0686d633adf1c5c97bcd64eaf6a7b641209","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}