{"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/benchmarking-the-communication-competence-of","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","arxiv_id":"2406.00215","date":"2024-05-31","proceeding":null,"authors":["Jie JW Wu","Fatemeh H Fard"],"abstract":"Large language models (LLMs) have significantly improved their ability to perform tasks in the field of code generation. However, there is still a gap between LLMs being capable coders and being top-tier software engineers. Based on the observation that top-level software engineers often ask clarifying questions to reduce ambiguity in both requirements and coding solutions, we argue that the same should be applied to LLMs for code generation tasks. In this work, we conducted an empirical study on the benchmark and analysis of the communication skills of LLMs for code generation. We define communication skills of LLMs as ``being able to ask clarifying questions when the description of the code generation problem has issues''. We created a new benchmark, HumanEvalComm, by modifying problem descriptions according to three issues: inconsistency, ambiguity, incompleteness. We defined new evaluation metrics such as Communication Rate and Good Question Rate, and then experimented on HumanEvalComm with different Code LLMs, and a new LLM agent approach, Okanagan, to identify and ask questions in ambiguous parts from code and descriptions for further refining the generated code. Finally, we discussed evaluation results by comparing Code LLMs and Okanagan with our findings.","url_abs":"https://arxiv.org/abs/2406.00215v3","url_pdf":"https://arxiv.org/pdf/2406.00215v3.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"benchmarking-the-communication-competence-of","repo_url":"https://github.com/jie-jw-wu/human-eval-comm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.00215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00215"}},"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":"deterministic:regex_extraction","url":"https://github.com/jie-jw-wu/human-eval-comm","reach":{"status":"ok"}}],"summary":{"ran":12,"unverified":7},"by_repo_kind":{"official":{"samples":19,"ran":12,"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":19,"samples":[{"code_sha256_prefix":"0bf323d93f03b832","entry":"extract_prefix","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"measurement_summary_draw_heatmap.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/measurement_summary_draw_heatmap.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0bf323d93f03b832"}},{"code_sha256_prefix":"7f8144a905f5b101","entry":"generate_text","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"generate_response.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/generate_response.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7f8144a905f5b101"}},{"code_sha256_prefix":"5dba7da2cfd89116","entry":"get_ask_question_rate","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"syntactic_similarity_OER.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/syntactic_similarity_OER.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5dba7da2cfd89116"}},{"code_sha256_prefix":"b088fc0024baa28f","entry":"get_ask_question_rate_with_qq","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"syntactic_similarity_OER.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/syntactic_similarity_OER.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b088fc0024baa28f"}},{"code_sha256_prefix":"491a124a37148dfd","entry":"preprocess_data","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"AgentFramework/designer.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/AgentFramework/designer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"491a124a37148dfd"}},{"code_sha256_prefix":"b231819920453b1d","entry":"preprocess_data","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"AgentFramework/executor.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/AgentFramework/executor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b231819920453b1d"}},{"code_sha256_prefix":"854e64377cfc300a","entry":"preprocess_data","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"AgentFramework/programmer.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/AgentFramework/programmer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"854e64377cfc300a"}},{"code_sha256_prefix":"2e3b2a31d4b30e77","entry":"programmer_main","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"AgentFramework/programmer.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/AgentFramework/programmer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e3b2a31d4b30e77"}},{"code_sha256_prefix":"3a8a940a00b74328","entry":"ratio_of_worst","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"measurement_summary_draw_heatmap.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/measurement_summary_draw_heatmap.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a8a940a00b74328"}},{"code_sha256_prefix":"ed2c1ad3bc24cdc8","entry":"response_2_code","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"intermedia_analyze.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/intermedia_analyze.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ed2c1ad3bc24cdc8"}},{"code_sha256_prefix":"44d500098cd18911","entry":"solution_evaluation","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"intermedia_analyze.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/intermedia_analyze.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44d500098cd18911"}},{"code_sha256_prefix":"cd60fe0a3a7d62ad","entry":"solution_evaluation_HumanEval","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"intermedia_analyze.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/intermedia_analyze.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd60fe0a3a7d62ad"}},{"code_sha256_prefix":"509467404a76b343","entry":"analyze_among_top0_5","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"syntactic_similarity_OER.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/syntactic_similarity_OER.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"509467404a76b343"}},{"code_sha256_prefix":"310e25d69d224637","entry":"designer_main","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"AgentFramework/designer.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/AgentFramework/designer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"310e25d69d224637"}},{"code_sha256_prefix":"c8ae809824048769","entry":"fetch_completion","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"AgentFramework/designer.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/AgentFramework/designer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c8ae809824048769"}},{"code_sha256_prefix":"19a9b628e7fcf1e1","entry":"fetch_completion","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"AgentFramework/programmer.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/AgentFramework/programmer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"19a9b628e7fcf1e1"}},{"code_sha256_prefix":"e5fc7b939577a999","entry":"get_completion_starchat_nl_to_pl","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"generate_response.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/generate_response.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e5fc7b939577a999"}},{"code_sha256_prefix":"1fcf5236ce19bc6e","entry":"get_completion_starchat_pl_to_nl","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"generate_response.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/generate_response.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1fcf5236ce19bc6e"}},{"code_sha256_prefix":"5eef0e3253e15ffa","entry":"semantic_syntactic_structural_similarity","repo":"jie-jw-wu/human-eval-comm","repo_kind":"official","path":"measurement_summary_draw_heatmap.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/measurement_summary_draw_heatmap.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5eef0e3253e15ffa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}