{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/seeing-the-big-through-the-small-can-llms","title":"\"Seeing the Big through the Small\": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?","arxiv_id":"2406.17600","date":"2024-06-25","proceeding":null,"authors":["Beiduo Chen","Xinpeng Wang","Siyao Peng","Robert Litschko","Anna Korhonen","Barbara Plank"],"abstract":"Human label variation (HLV) is a valuable source of information that arises when multiple human annotators provide different labels for valid reasons. In Natural Language Inference (NLI) earlier approaches to capturing HLV involve either collecting annotations from many crowd workers to represent human judgment distribution (HJD) or use expert linguists to provide detailed explanations for their chosen labels. While the former method provides denser HJD information, obtaining it is resource-intensive. In contrast, the latter offers richer textual information but it is challenging to scale up to many human judges. Besides, large language models (LLMs) are increasingly used as evaluators (\"LLM judges\") but with mixed results, and few works aim to study HJDs. This study proposes to exploit LLMs to approximate HJDs using a small number of expert labels and explanations. Our experiments show that a few explanations significantly improve LLMs' ability to approximate HJDs with and without explicit labels, thereby providing a solution to scale up annotations for HJD. However, fine-tuning smaller soft-label aware models with the LLM-generated model judgment distributions (MJDs) presents partially inconsistent results: while similar in distance, their resulting fine-tuned models and visualized distributions differ substantially. We show the importance of complementing instance-level distance measures with a global-level shape metric and visualization to more effectively evaluate MJDs against human judgment distributions.","url_abs":"https://arxiv.org/abs/2406.17600v2","url_pdf":"https://arxiv.org/pdf/2406.17600v2.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":"seeing-the-big-through-the-small-can-llms","repo_url":"https://github.com/mainlp/mjd-estimator","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.17600","atlas_url":"https://app.syntology.ai/?focus=2406.17600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17600"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mainlp/mjd-estimator","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b64795c5579a5808","entry":"dotdict_collate","repo":"mainlp/mjd-estimator","repo_kind":"official","path":"MJD-fine-tuning/loader/common.py","file_url":"https://github.com/mainlp/mjd-estimator/blob/HEAD/MJD-fine-tuning/loader/common.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b64795c5579a5808"}},{"code_sha256_prefix":"18b7851b76ccbc5a","entry":"convert_examples_to_features","repo":"mainlp/mjd-estimator","repo_kind":"official","path":"MJD-fine-tuning/loader/common.py","file_url":"https://github.com/mainlp/mjd-estimator/blob/HEAD/MJD-fine-tuning/loader/common.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"18b7851b76ccbc5a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}