Papers › MultifacetEval: Multifaceted Evaluation to Probe LLMs in Mastering Medical Knowledge

MultifacetEval: Multifaceted Evaluation to Probe LLMs in Mastering Medical Knowledge

5 Jun 2024arXiv:2406.02919archive 2025-07-28

Yuxuan Zhou, Xien Liu, Chen Ning, Ji Wu

Large language models (LLMs) have excelled across domains, also delivering notable performance on the medical evaluation benchmarks, such as MedQA. However, there still exists a significant gap between the reported performance and the practical effectiveness in real-world medical scenarios. In this paper, we aim to explore the causes of this gap by employing a multifaceted examination schema to systematically probe the actual mastery of medical knowledge by current LLMs. Specifically, we develop a novel evaluation framework MultifacetEval to examine the degree and coverage of LLMs in encoding and mastering medical knowledge at multiple facets (comparison, rectification, discrimination, and verification) concurrently. Based on the MultifacetEval framework, we construct two multifaceted evaluation datasets: MultiDiseK (by producing questions from a clinical disease knowledge base) and MultiMedQA (by rephrasing each question from a medical benchmark MedQA into multifaceted questions). The experimental results on these multifaceted datasets demonstrate that the extent of current LLMs in mastering medical knowledge is far below their performance on existing medical benchmarks, suggesting that they lack depth, precision, and comprehensiveness in mastering medical knowledge. Consequently, current LLMs are not yet ready for application in real-world medical tasks. The codes and datasets are available at https://github.com/THUMLP/MultifacetEval.

PaperPDFCodeCode Syntology ranMethod as code

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 24 code samples harvested from 1 repository linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 20 ran (11 with no instrument failure; 9 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. 1 of the 20 samples that ran has no recorded date.

thumlp/multifaceteval officialmentioned in paperpytorchMITSyntology: 24 samples, 20 ran (9 instrument-failed) · 4 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

24 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 9 where Syntology's instrument failed) · 4 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.

9ran · our draft was wrong
11ran
4unverified

Licence: 1 of the 24 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from thumlp/multifaceteval. “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.

thumlp/multifaceteval official repository 24 samples, 20 ran (9 instrument-failed) · 4 unverified
load_data in 700 papers evaluate_gemini_medqa_ao.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 8dadf8eedaeb7704 · report fixture: signature path:str/0/str · returned dict · level recorded, date not recorded
answer_vote MAQ_answer_analysis_medqa_cotsc.py ran · our draft was wrong MIT (permissive) · 1914087ade7e8bca · report fixture: signature preds:list/1/list · returned list · level recorded 2026-09-24
answer_vote TFQ_answer_analysis_medqa_cotsc.py ran · our draft was wrong fingerprinted MIT (permissive) · bad8bcc825e86b66 · report fixture: signature answers:list/1/str · returned str · level recorded 2026-09-24
cal_relative_performance analysis.py ran · our draft was wrong MIT (permissive) · eaec6bcf4919e973 · report fixture: signature results:dict/0/? · returned dict · level recorded 2026-09-24
chating evaluate_gemini_medqa_ao.py ran MIT (permissive) · 4310ef2a5f4665b3 · report fixture: signature tmp_input:str/0/str, dev_data:list/1/tuple, neg:bool/0/bool, num_examples:int/0/int, model:MockGeminiModel/0/?, task:str/0/str, repeat:int/0/int · returned str · level recorded 2026-09-24
chating evaluate_gemini_medqa_cotsc.py ran MIT (permissive) · e0a0dd11c62a40fc · report fixture: signature tmp_input:str/0/str, dev_data:list/1/tuple, neg:bool/0/bool, num_examples:int/0/int, model:MockModel/0/?, task:str/0/str, repeat:int/0/int · returned str · level recorded 2026-09-24
chating evaluate_gpt_medqa_ao.py ran MIT (permissive) · 20ea85577d06ac6d · report fixture: signature tmp_input:str/0/str, dev_data:list/1/tuple, neg:bool/0/bool, num_examples:int/0/int, model:str/0/str, task:str/0/str, repeat:int/0/int · returned str · level recorded 2026-09-24
extract_ans in 9 papers MAQ_answer_analysis_medqa.py ran MIT (permissive) · a621bd45961d965f · report fixture: signature response_str:str/0/str, options:dict/0/? · returned list · level recorded 2026-09-24
extract_ans in 9 papers MAQ_answer_analysis_medqa_cotsc.py ran MIT (permissive) · 24796f0e8267d08f · report fixture: signature response_str:str/0/str, options:dict/0/? · returned list · level recorded 2026-09-24
extract_ans in 9 papers MCQ_answer_analysis_medqa.py ran MIT (permissive) · 5fe4ca43949d2549 · report fixture: signature response_str:str/0/str, options:dict/0/? · returned list · level recorded 2026-09-24
extract_ans in 9 papers MCQ_answer_analysis_medqa_cotsc.py ran MIT (permissive) · 172aa259fd1693c0 · report fixture: signature response_str:str/0/str, options:dict/0/? · returned tuple · level recorded 2026-09-24
extract_ans in 9 papers RQ_answer_analysis_medqa.py ran MIT (permissive) · be9589b46024780d · report fixture: signature response_str:str/0/str, options:dict/0/? · returned list · level recorded 2026-09-24
extract_ans in 9 papers RQ_answer_analysis_medqa_cotsc.py ran MIT (permissive) · 66dd4af07fab516b · report fixture: signature response_str:str/0/str, options:dict/0/?, alice_ans:str/0/str · returned list · level recorded 2026-09-24
extract_ans in 9 papers TFQ_answer_analysis_medqa.py ran · our draft was wrong fingerprinted MIT (permissive) · e508780be7f14ee4 · report fixture: signature response_str:str/0/str · returned str · level recorded 2026-09-24
extract_ans in 9 papers TFQ_answer_analysis_medqa_cotsc.py ran · our draft was wrong fingerprinted MIT (permissive) · 685e445c8af90359 · report fixture: signature response_str:str/0/str · returned str · level recorded 2026-09-24
extract_judge_ans RQ_answer_analysis_medqa.py ran · our draft was wrong fingerprinted MIT (permissive) · 2afd82f1ded8da3d · report fixture: signature response_str:str/0/str · returned str · level recorded 2026-09-24
extract_judge_ans RQ_answer_analysis_medqa_cotsc.py ran · our draft was wrong fingerprinted MIT (permissive) · adc04b1d9b3eac03 · report fixture: signature response_str:str/0/str · returned str · level recorded 2026-09-24
option_vote MAQ_answer_analysis_medqa_cotsc.py ran · our draft was wrong MIT (permissive) · eb38f86f64a280f1 · report fixture: signature preds:list/1/list · returned list · level recorded 2026-09-24
prepare_examples evaluate_gemini_medqa_ao.py ran MIT (permissive) · 50ad33216c34d9df · report fixture: signature dev_data:list/1/tuple, neg:bool/0/bool, nums:int/0/int, task:str/0/str · returned str · level recorded 2026-09-24
prepare_examples evaluate_gemini_medqa_cotsc.py ran MIT (permissive) · d1c4dd08b81436c2 · report fixture: signature dev_data:list/1/tuple, neg:bool/0/bool, nums:int/0/int, task:str/0/str · returned str · level recorded 2026-09-24
analyze_results in 5 papers analysis.py unverified MIT (permissive) · f1992607d65dde76 · report
extract_option_ans RQ_answer_analysis_medqa.py unverified MIT (permissive) · 362d000f1db36524 · report
extract_option_ans RQ_answer_analysis_medqa_cotsc.py unverified MIT (permissive) · c092350d57b92b7c · report
recognize_and_rewrite recognize_and_rewrite_medqa.py unverified MIT (permissive) · 5a00271a076bdc13 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MultifacetEval (graph method: MultifacetEval). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. recognize_and_rewrite entry · level 0 · unverified · 5a00271a076bdc13

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2406.02919") returns these assemblies with each brick's role and wiring (how to connect).

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