Papers › ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented...

ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models

28 Jun 2024arXiv:2406.20015archive 2025-07-28

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

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

toolbehonest/toolbehonest officialmentioned in papermentioned on GitHubMITSyntology: 10 samples, 8 ran (3 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
4ran
2unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from toolbehonest/toolbehonest. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

toolbehonest/toolbehonest official repository 10 samples, 8 ran (3 instrument-failed) · 2 unverified
calculate_group_metrics utils/calculate_metrics.py ran MIT (permissive) · 6fb1a0169bd1be3b · report fixture: signature metrics:dict/0/?, tasks:list/1/str, level:str/0/str · returned list · level recorded 2026-09-24
calculate_metrics in 61 papers utils/calculate_metrics.py ran MIT (permissive) · 391471f665ef5fbb · report fixture: signature metrics:dict/0/?, task:str/0/str, level:str/0/str · returned float64 · level recorded 2026-09-24
calculate_progress_rate utils/evaluation_func.py ran MIT (permissive) · b3f0a50ef6d3855a · report fixture: signature pred_planning_tool_list:list/1/str, golden_planning_tool_list:list/1/str, calculate_type:str/0/str · returned float · level recorded 2026-09-24
calculate_scorers utils/evaluation_func.py ran MIT (permissive) · 48f662460933098c · report fixture: signature pred_subgoal_texts:list/1/str, pred_planning_tool_list:list/1/str, golden_planning_tool_list:list/1/str, origin_provided_subgoal_dict:dict/0/?, solvable_planning_tool_list:list/1/str, emb_model:callable/0/?, tools_embedding:dict/0/?, task:str/0/str, args:MockArgs/0/? · returned list · level recorded 2026-09-24
convert_hf_data utils/process.py ran · our draft was wrong MIT (permissive) · 4df6e9bfa123391f · report fixture: signature items:list/1/dict · returned dict · level recorded 2026-09-24
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
utils/calculate_metrics.py ran · honoured contract fingerprinted MIT (permissive) · 85def4810dd23c07 · report fixture: signature data:list/1/int · returned list · level recorded 2026-09-24
rate_limited utils/generation_func.py ran · our draft was wrong MIT (permissive) · d5c69ffdd4162e91 · report fixture: signature max_per_minute:int/0/int · returned function · level recorded 2026-09-24
remove_finish_if_last utils/extract_func.py ran · our draft was wrong MIT (permissive) · 26fbd3a16ca609af · report fixture: signature tools:list/1/str · returned list · level recorded 2026-09-24
get_tools_embeddings utils/generation_func.py unverified MIT (permissive) · 638f0013e2a9e95f · report
load_results in 82 papers utils/load_save.py unverified MIT (permissive) · 4cfcb6ed2385c374 · report

Tasks

DiagnosticHallucination

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections