{"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/interpretable-unified-language-checking","title":"Interpretable Unified Language Checking","arxiv_id":"2304.03728","date":"2023-04-07","proceeding":null,"authors":["Tianhua Zhang","Hongyin Luo","Yung-Sung Chuang","Wei Fang","Luc Gaitskell","Thomas Hartvigsen","Xixin Wu","Danny Fox","Helen Meng","James Glass"],"abstract":"Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-task language checkers based on their latent representations of natural and social knowledge. We present an interpretable, unified, language checking (UniLC) method for both human and machine-generated language that aims to check if language input is factual and fair. While fairness and fact-checking tasks have been handled separately with dedicated models, we find that LLMs can achieve high performance on a combination of fact-checking, stereotype detection, and hate speech detection tasks with a simple, few-shot, unified set of prompts. With the ``1/2-shot'' multi-task language checking method proposed in this work, the GPT3.5-turbo model outperforms fully supervised baselines on several language tasks. The simple approach and results suggest that based on strong latent knowledge representations, an LLM can be an adaptive and explainable tool for detecting misinformation, stereotypes, and hate speech.","url_abs":"https://arxiv.org/abs/2304.03728v1","url_pdf":"https://arxiv.org/pdf/2304.03728v1.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":"interpretable-unified-language-checking","repo_url":"https://github.com/luohongyin/unilc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"hate-speech-detection","task_name":"Hate Speech Detection"},{"task_slug":"misinformation","task_name":"Misinformation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.03728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03728"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/luohongyin/unilc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"eb66c0e079e6c95b","entry":"build_background","repo":"luohongyin/unilc","repo_kind":"official","path":"general_check.py","file_url":"https://github.com/luohongyin/unilc/blob/HEAD/general_check.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb66c0e079e6c95b"}},{"code_sha256_prefix":"325eaa5afe81ed34","entry":"evaluate","repo":"luohongyin/unilc","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/luohongyin/unilc/blob/HEAD/analysis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"325eaa5afe81ed34"}},{"code_sha256_prefix":"65e9e5cbfa740b96","entry":"fact_class","repo":"luohongyin/unilc","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/luohongyin/unilc/blob/HEAD/analysis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65e9e5cbfa740b96"}},{"code_sha256_prefix":"2f07bcf7ab0ce11a","entry":"is_answerable","repo":"luohongyin/unilc","repo_kind":"official","path":"general_check.py","file_url":"https://github.com/luohongyin/unilc/blob/HEAD/general_check.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f07bcf7ab0ce11a"}},{"code_sha256_prefix":"128c65994fabc3e2","entry":"load_dataset","repo":"luohongyin/unilc","repo_kind":"official","path":"general_check.py","file_url":"https://github.com/luohongyin/unilc/blob/HEAD/general_check.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"128c65994fabc3e2"}},{"code_sha256_prefix":"3c472e1547a3c5cb","entry":"load_eval_data","repo":"luohongyin/unilc","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/luohongyin/unilc/blob/HEAD/analysis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c472e1547a3c5cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}