SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.04306 · ICLR · 2025

Improving Uncertainty Estimation through Semantically Diverse Language Generation

Sepp Hochreiter, Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi

arXiv · PDF · Open in the Atlas

Code that ran

5 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 6 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.04306.json · badge: /api/ran/2406.04306.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ml-jku/SDLG canonical (classifier label)
classifier basis: classifier_2025
5 ran · 6 no recorded run
FunctionStatusWhere it lives
clean_generation Ran
ran; our contract draft was wrong, not the code
ml-jku/SDLG/sdlg.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("c079bf5aa1e65d85")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_likelihood Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ml-jku/SDLG/sdlg.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("e32e20f5d1a27c3b")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_word_indices Ran
ran; our contract draft was wrong, not the code
ml-jku/SDLG/sdlg.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("4fc5bd5d74bb816b")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rank_tensor Ran
ran; our contract draft was wrong, not the code
ml-jku/SDLG/sdlg.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("c8008859407c4f6a")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

remove_invalid_ids Ran
ran; our contract draft was wrong, not the code
ml-jku/SDLG/sdlg.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("1a6208fbe06fee8d")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_token_score_ranking Not yet run
unverified (harvested, no recorded run)
ml-jku/SDLG/sdlg.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("95a922573781d7aa")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

encode Not yet run
unverified (harvested, no recorded run)
ml-jku/SDLG/run_experiments.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("8d9f3ee549cef855")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

encode_and_format_dataset Not yet run
unverified (harvested, no recorded run)
ml-jku/SDLG/run_experiments.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("d4e612315aff11dd")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

forward_hook Not yet run
unverified (harvested, no recorded run)
ml-jku/SDLG/sdlg.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("6974d8f454f15c31")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

generate_semantically_diverse_output_sequences Not yet run
unverified (harvested, no recorded run)
ml-jku/SDLG/sdlg.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("4cdc3aa9b371f7d6")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

generate_text Not yet run
unverified (harvested, no recorded run)
ml-jku/SDLG/sdlg.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("a701b90b916f5466")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, ml-jku/SDLG, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 11 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models (LLMs) can suffer from hallucinations when generating text. These hallucinations impede various applications in society and industry by making LLMs untrustworthy. Current LLMs generate text in an autoregressive fashion by predicting and appending text tokens. When an LLM is uncertain about the semantic meaning of the next tokens to generate, it is likely to start hallucinating. Thus, it has been suggested that predictive uncertainty is one of the main causes of hallucinations. We introduce Semantically Diverse Language Generation (SDLG) to quantify predictive uncertainty in LLMs. SDLG steers the LLM to generate semantically diverse yet likely alternatives for an initially generated text. This approach provides a precise measure of aleatoric semantic uncertainty, detecting whether the initial text is likely to be hallucinated. Experiments on question-answering tasks demonstrate that SDLG consistently outperforms existing methods while being the most computationally efficient, setting a new standard for uncertainty estimation in LLMs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.04306")
get_code_for_paper("2406.04306")
have("2406.04306")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.04306.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.04306.svg)](https://syntology.ai/paper/2406.04306)

Connect an agent — have() is free.