{"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/toolbehonest-a-multi-level-hallucination","title":"ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models","arxiv_id":"2406.20015","date":"2024-06-28","proceeding":null,"authors":["Yuxiang Zhang","Jing Chen","Junjie Wang","Yaxin Liu","Cheng Yang","Chufan Shi","Xinyu Zhu","Zihao Lin","Hanwen Wan","Yujiu Yang","Tetsuya Sakai","Tian Feng","Hayato Yamana"],"abstract":"Tool-augmented large language models (LLMs) are rapidly being integrated into real-world applications. Due to the lack of benchmarks, the community has yet to fully understand the hallucination issues within these models. To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH. Specifically, we assess the LLM's hallucinations through two perspectives: depth and breadth. In terms of depth, we propose a multi-level diagnostic process, including (1) solvability detection, (2) solution planning, and (3) missing-tool analysis. For breadth, we consider three scenarios based on the characteristics of the toolset: missing necessary tools, potential tools, and limited functionality tools. Furthermore, we developed seven tasks and collected 700 evaluation samples through multiple rounds of manual annotation. The results show the significant challenges presented by the ToolBH benchmark. The current advanced models Gemini-1.5-Pro and GPT-4o only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100. In this benchmark, larger model parameters do not guarantee better performance; the training data and response strategies also play crucial roles in tool-enhanced LLM scenarios. Our diagnostic analysis indicates that the primary reason for model errors lies in assessing task solvability. Additionally, open-weight models suffer from performance drops with verbose replies, whereas proprietary models excel with longer reasoning.","url_abs":"https://arxiv.org/abs/2406.20015v2","url_pdf":"https://arxiv.org/pdf/2406.20015v2.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":"toolbehonest-a-multi-level-hallucination","repo_url":"https://github.com/toolbehonest/toolbehonest","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"hallucination","task_name":"Hallucination"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.20015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20015"}},"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/toolbehonest/toolbehonest","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":"6fb1a0169bd1be3b","entry":"calculate_group_metrics","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/calculate_metrics.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/calculate_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6fb1a0169bd1be3b"}},{"code_sha256_prefix":"391471f665ef5fbb","entry":"calculate_metrics","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/calculate_metrics.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/calculate_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"391471f665ef5fbb"}},{"code_sha256_prefix":"b3f0a50ef6d3855a","entry":"calculate_progress_rate","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/evaluation_func.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/evaluation_func.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3f0a50ef6d3855a"}},{"code_sha256_prefix":"48f662460933098c","entry":"calculate_scorers","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/evaluation_func.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/evaluation_func.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48f662460933098c"}},{"code_sha256_prefix":"4df6e9bfa123391f","entry":"convert_hf_data","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/process.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/process.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4df6e9bfa123391f"}},{"code_sha256_prefix":"85def4810dd23c07","entry":"flatten","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/calculate_metrics.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/calculate_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85def4810dd23c07"}},{"code_sha256_prefix":"d5c69ffdd4162e91","entry":"rate_limited","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/generation_func.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/generation_func.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d5c69ffdd4162e91"}},{"code_sha256_prefix":"26fbd3a16ca609af","entry":"remove_finish_if_last","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/extract_func.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/extract_func.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26fbd3a16ca609af"}},{"code_sha256_prefix":"638f0013e2a9e95f","entry":"get_tools_embeddings","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/generation_func.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/generation_func.py","link_basis":"first_harvest_node","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":"638f0013e2a9e95f"}},{"code_sha256_prefix":"4cfcb6ed2385c374","entry":"load_results","repo":"toolbehonest/toolbehonest","repo_kind":"official","path":"utils/load_save.py","file_url":"https://github.com/toolbehonest/toolbehonest/blob/HEAD/utils/load_save.py","link_basis":"first_harvest_node","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":"4cfcb6ed2385c374"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}