{"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/are-llm-based-evaluators-confusing-nlg","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria?","arxiv_id":"2402.12055","date":"2024-02-19","proceeding":null,"authors":["Xinyu Hu","Mingqi Gao","Sen Hu","Yang Zhang","Yicheng Chen","Teng Xu","Xiaojun Wan"],"abstract":"Some prior work has shown that LLMs perform well in NLG evaluation for different tasks. However, we discover that LLMs seem to confuse different evaluation criteria, which reduces their reliability. For further verification, we first consider avoiding issues of inconsistent conceptualization and vague expression in existing NLG quality criteria themselves. So we summarize a clear hierarchical classification system for 11 common aspects with corresponding different criteria from previous studies involved. Inspired by behavioral testing, we elaborately design 18 types of aspect-targeted perturbation attacks for fine-grained analysis of the evaluation behaviors of different LLMs. We also conduct human annotations beyond the guidance of the classification system to validate the impact of the perturbations. Our experimental results reveal confusion issues inherent in LLMs, as well as other noteworthy phenomena, and necessitate further research and improvements for LLM-based evaluation.","url_abs":"https://arxiv.org/abs/2402.12055v2","url_pdf":"https://arxiv.org/pdf/2402.12055v2.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":"are-llm-based-evaluators-confusing-nlg","repo_url":"https://github.com/herrxy/llm-evaluator-reliability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"are-llm-based-evaluators-confusing-nlg","repo_url":"https://github.com/pku-onelab/llm-evaluator-reliability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"nlg-evaluation","task_name":"nlg evaluation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.12055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12055"}},"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/herrxy/llm-evaluator-reliability","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pku-onelab/llm-evaluator-reliability","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":3,"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":"1e3e86a7baafca68","entry":"contains_non_alpha","repo":"herrxy/llm-evaluator-reliability","repo_kind":"official","path":"Perturbations/grammar_order.py","file_url":"https://github.com/herrxy/llm-evaluator-reliability/blob/HEAD/Perturbations/grammar_order.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":"1e3e86a7baafca68"}},{"code_sha256_prefix":"26336d4815eced14","entry":"introduce_swap","repo":"herrxy/llm-evaluator-reliability","repo_kind":"official","path":"Perturbations/grammar_order.py","file_url":"https://github.com/herrxy/llm-evaluator-reliability/blob/HEAD/Perturbations/grammar_order.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26336d4815eced14"}},{"code_sha256_prefix":"97382afbeed4ecb1","entry":"introduce_typo","repo":"herrxy/llm-evaluator-reliability","repo_kind":"official","path":"Perturbations/grammar_typo.py","file_url":"https://github.com/herrxy/llm-evaluator-reliability/blob/HEAD/Perturbations/grammar_typo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"97382afbeed4ecb1"}},{"code_sha256_prefix":"a344135785b6fb9b","entry":"attack_coherence_sentence_order","repo":"herrxy/llm-evaluator-reliability","repo_kind":"official","path":"Perturbations/coherence_order.py","file_url":"https://github.com/herrxy/llm-evaluator-reliability/blob/HEAD/Perturbations/coherence_order.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":"a344135785b6fb9b"}},{"code_sha256_prefix":"acb43e2bc12c97cc","entry":"attack_grammar_typos","repo":"herrxy/llm-evaluator-reliability","repo_kind":"official","path":"Perturbations/grammar_typo.py","file_url":"https://github.com/herrxy/llm-evaluator-reliability/blob/HEAD/Perturbations/grammar_typo.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":"acb43e2bc12c97cc"}},{"code_sha256_prefix":"05e821e68b4582a4","entry":"attack_grammar_word_order","repo":"herrxy/llm-evaluator-reliability","repo_kind":"official","path":"Perturbations/grammar_order.py","file_url":"https://github.com/herrxy/llm-evaluator-reliability/blob/HEAD/Perturbations/grammar_order.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":"05e821e68b4582a4"}},{"code_sha256_prefix":"1d690ef0ad6fdfc4","entry":"attack_informative_delete_last","repo":"herrxy/llm-evaluator-reliability","repo_kind":"official","path":"Perturbations/inform_delete.py","file_url":"https://github.com/herrxy/llm-evaluator-reliability/blob/HEAD/Perturbations/inform_delete.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":"1d690ef0ad6fdfc4"}},{"code_sha256_prefix":"90afb16f86fbb016","entry":"is_the_same","repo":"herrxy/llm-evaluator-reliability","repo_kind":"official","path":"Perturbations/coherence_order.py","file_url":"https://github.com/herrxy/llm-evaluator-reliability/blob/HEAD/Perturbations/coherence_order.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":"90afb16f86fbb016"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}