Papers › Benchmarking LLMs via Uncertainty Quantification

Benchmarking LLMs via Uncertainty Quantification

23 Jan 2024arXiv:2401.12794archive 2025-07-28

Fanghua Ye, Mingming Yang, Jianhui Pang, Longyue Wang, Derek F. Wong, Emine Yilmaz, Shuming Shi, Zhaopeng Tu

The proliferation of open-source Large Language Models (LLMs) from various institutions has highlighted the urgent need for comprehensive evaluation methods. However, current evaluation platforms, such as the widely recognized HuggingFace open LLM leaderboard, neglect a crucial aspect -- uncertainty, which is vital for thoroughly assessing LLMs. To bridge this gap, we introduce a new benchmarking approach for LLMs that integrates uncertainty quantification. Our examination involves nine LLMs (LLM series) spanning five representative natural language processing tasks. Our findings reveal that: I) LLMs with higher accuracy may exhibit lower certainty; II) Larger-scale LLMs may display greater uncertainty compared to their smaller counterparts; and III) Instruction-finetuning tends to increase the uncertainty of LLMs. These results underscore the significance of incorporating uncertainty in the evaluation of LLMs.

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.

Syntology holds a reference implementation of benchmarking approach for LLMs that integrates uncertainty quantification, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='benchmarking approach for LLMs that integrates uncertainty quantification') (how to connect); the free check have('2401.12794') needs no token.

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

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 12 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 13 ran (1 with no instrument failure; 12 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 13 samples that ran have no recorded date.

smartyfh/llm-uncertainty-bench officialmentioned in papermentioned on GitHubpytorchMITSyntology: 17 samples, 13 ran (12 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

17 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 12 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 has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
12ran · our draft was wrong
4unverified

Licence: 1 of the 17 samples is 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 smartyfh/llm-uncertainty-bench. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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.

smartyfh/llm-uncertainty-bench official repository 17 samples, 13 ran (12 instrument-failed) · 4 unverified
load_data in 700 papers generate_logits.py ran · our draft was wrong MIT (permissive) · 9cb5a160cb942951 · report fixture: signature data_file:str/0/str · returned dict · level recorded, date not recorded
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket this sample: bucket 2 of 8, arg 1: rank 1, kind float, dtype float64
uncertainty_quantification_via_cp.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · violated contract fingerprinted licence of this copy not recorded · 7f9b15275ca5759c · report fixture: signature x:ndarray/1/float · returned ndarray · level recorded, date not recorded
cal_acc in 10 papers uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · 1a38d8124050f460 · report fixture: signature logits_data_all:dict/0/?, test_raw_data:list/1/dict, prompt_methods:list/1/str, icl_methods:list/1/str · returned tuple · level recorded 2026-09-24
cal_coverage uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · 2d8b9343c19529f9 · report fixture: signature pred_sets_all:dict/0/?, test_id_to_answer:dict/0/?, prompt_methods:list/1/str, icl_methods:list/1/str · returned dict · level recorded 2026-09-24
cal_set_size uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · b53afba9c0da9944 · report fixture: signature pred_sets_all:dict/0/?, prompt_methods:list/1/str, icl_methods:list/1/str · returned dict · level recorded 2026-09-24
cal_uacc uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · 50a4b22e789fd992 · report fixture: signature results_acc:dict/0/?, set_sizes:dict/0/? · returned dict · level recorded 2026-09-22
convert_id_to_ans uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · 037e99602ccc4435 · report fixture: signature test_raw_data:list/1/dict · returned dict · level recorded 2026-09-22
get_accuracy in 52 papers
census: 4 implementations from 6 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · 7027200b9089953e · report fixture: signature logits_data:list/1/dict, raw_data:list/1/dict · returned tuple · level recorded 2026-09-22
get_fewshot_exps generate_logits.py ran · our draft was wrong MIT (permissive) · 50b7e2a98d17a3d4 · report fixture: signature data:list/1/dict · returned list · level recorded, date not recorded
get_logits_data uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · fc79c5e7f5428533 · report fixture: signature model_name:str/0/str, data_name:str/0/str, cal_raw_data:list/1/dict, test_raw_data:list/1/dict, logits_data_dir:str/0/str, cal_ratio:float/0/float, prompt_methods:list/1/str, icl_methods:list/1/str · returned dict · level recorded, date not recorded
get_logits_data uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · d27097c4a183befa · report fixture: signature model_name:str/0/str, data_name:str/0/str, cal_raw_data:list/1/dict, test_raw_data:list/1/dict, logits_data_dir:str/0/str, cal_ratio:float/0/float, prompt_methods:list/1/str, icl_methods:list/1/str · returned dict · level recorded 2026-09-24
get_raw_data in 9 papers uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · 756bbcda282e506a · report fixture: signature raw_data_dir:str/0/str, data_name:str/0/str, cal_ratio:float/0/float · returned tuple · level recorded, date not recorded
get_raw_data in 9 papers uncertainty_quantification_via_cp.py ran · our draft was wrong MIT (permissive) · f1da4e31dbe5407b · report fixture: signature raw_data_dir:str/0/str, data_name:str/0/str, cal_ratio:float/0/float · returned tuple · level recorded 2026-09-24
APS_CP uncertainty_quantification_via_cp.py unverified MIT (permissive) · 6fc15eb0d745506b · report
LAC_CP uncertainty_quantification_via_cp.py unverified MIT (permissive) · 8f79d57c0ec1f93b · report
apply_conformal_prediction uncertainty_quantification_via_cp.py unverified MIT (permissive) · 051cab8f58895ebd · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for benchmarking approach for LLMs that integrates uncertainty quantification (graph method: benchmarking approach for LLMs that integrates uncertainty quantification), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. calculate_conformal_threshold entry · level 3 · ran · violated contract · 6e324e35f8a7aeacfefbff72565cceeec0d8c48f6f4cf1e3c3b2eae11b26c741

harvested Assembly for benchmarking approach for LLMs that integrates uncertainty quantification (graph method: benchmarking approach for LLMs that integrates uncertainty quantification). 12 bricks; individually on a fixture: 9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. apply_conformal_prediction entry · level 0 · unverified · 051cab8f58895ebd
  2. APS_CP metric · level 0 · unverified · 6fc15eb0d745506b
  3. LAC_CP metric · level 0 · unverified · 8f79d57c0ec1f93b
  4. cal_acc metric · level 1 · ran · our draft was wrong · 1a38d8124050f460
  5. cal_coverage metric · level 1 · ran · our draft was wrong · 2d8b9343c19529f9
  6. cal_set_size metric · level 1 · ran · our draft was wrong · b53afba9c0da9944
  7. cal_uacc metric · level 1 · ran · our draft was wrong · 50a4b22e789fd992
  8. convert_id_to_ans helper · level 1 · ran · our draft was wrong · 037e99602ccc4435
  9. get_logits_data data_transform · level 1 · ran · our draft was wrong · d27097c4a183befa
  10. get_raw_data data_transform · level 1 · ran · our draft was wrong · f1da4e31dbe5407b
  11. softmax helper · level 2 · ran · violated contract · 7f9b15275ca5759c
  12. get_accuracy helper · level 1 · ran · our draft was wrong · 7027200b9089953e

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="2401.12794") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

BenchmarkingUncertainty Quantification

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