SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.26366 · ICML · 2026

Automatic Layer Selection for Hallucination Detection

Andrew Wilson, Zhe Zeng, Xinpeng Wang, William Cao

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 4 failures of our instrument; 0 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/2605.26366.json · badge: /api/ran/2605.26366.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
DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
calc_rankme Ran
ran; our contract draft was wrong, not the code
DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection/method/rankme.py
pointer only (licence: NONE) · get_code("7b03562bcdcbf42a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection when it was checked. 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.

construct_input Ran
ran; our contract draft was wrong, not the code
DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection/src/utils.py
pointer only (licence: NONE) · get_code("1efe2dc8ead2f1a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection when it was checked. 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.

curvature Ran
ran; our contract draft was wrong, not the code
DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection/method/curvature.py
pointer only (licence: NONE) · get_code("075a2d53dec2eee4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection when it was checked. 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.

normalize_text Ran
ran; our contract draft was wrong, not the code
DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection/src/metrics.py
pointer only (licence: NONE) · get_code("4e686c57f3e71d5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection when it was checked. 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

FunctionAlso present inEarliest-datedOthers named
normalize_text 1 other paper
1 dated earlier
2402.18048 (2024-02)
Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension

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

Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language models (LLMs). Although a growing body of work has sought to exploit this property for hallucination detection, how to automate the selection of high-performing layers remains underexplored, and principled methods for this purpose are still lacking. To address this gap, we first propose several hypotheses for why such signals emerge in intermediate layers and evaluate corresponding criteria for automatic layer selection across diverse LLM architectures, scales, and tasks, covering both question answering and summarization hallucination detection benchmarks. However, we find that none of these criteria consistently delivers satisfactory performance. We therefore propose a new selection criterion, First Effective Peak of Intrinsic Dimension (FEPoID), which consistently identify optimal or near-optimal layers and outperforms both the aforementioned criteria and existing hallucination detection baselines. FEPoID is training-free and incurs negligible computational overhead. In addition, we study the generation behaviors of LLMs and introduce a simple yet effective truncation strategy, which further amplifies hallucinationrelated signals and substantially improves overall detection performance. Code is publicly available at https://github.com/DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection.git

For agents

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

get_harvested_code_for_paper("2605.26366")
get_code_for_paper("2605.26366")
have("2605.26366")

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

curl https://syntology.ai/api/ran/2605.26366.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.26366.svg)](https://syntology.ai/paper/2605.26366)

Connect an agent — have() is free.