SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.10117 · ICML · 2026

Biases in the Blind Spot: Detecting What LLMs Fail to Mention

Oana-Maria Camburu, Adrià Garriga-Alonso, Iván Arcuschin, David Chanin, Shared Context

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 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/2602.10117.json · badge: /api/ran/2602.10117.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
FlyingPumba/biases-in-the-blind-spot canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
apply_chat_template Ran
ran, honoured the contract we drafted
FlyingPumba/biases-in-the-blind-spot/biases_in_the_blind_spot/prompting.py
pointer only (licence: NONE) · get_code("8d2a192c16537e25")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlyingPumba/biases-in-the-blind-spot 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.

cos_sims Ran
ran; our contract draft was wrong, not the code
FlyingPumba/biases-in-the-blind-spot/biases_in_the_blind_spot/util.py
pointer only (licence: NONE) · get_code("96979417e88ed5b2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlyingPumba/biases-in-the-blind-spot 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.

default_deduplication_parser Ran
ran, violated the contract we drafted
FlyingPumba/biases-in-the-blind-spot/biases_in_the_blind_spot/concept_pipeline/concept_deduplicator.py
pointer only (licence: NONE) · get_code("efaf20207e7eb016")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlyingPumba/biases-in-the-blind-spot 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.

ensure_decompressed Ran
ran; our contract draft was wrong, not the code
FlyingPumba/biases-in-the-blind-spot/biases_in_the_blind_spot/util.py
pointer only (licence: NONE) · get_code("c2f87287daa33971")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlyingPumba/biases-in-the-blind-spot 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.

add_chat_template Not yet run
unverified (harvested, no recorded run)
FlyingPumba/biases-in-the-blind-spot/biases_in_the_blind_spot/llm_bias/model_utils.py
pointer only (licence: NONE) · get_code("990135fc571e139c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlyingPumba/biases-in-the-blind-spot 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. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We call these unverbalized biases. Monitoring models via their stated reasoning is therefore unreliable, and existing bias evaluations typically require predefined categories and hand-crafted datasets. In this work, we introduce a fully automated, black-box pipeline for detecting taskspecific unverbalized biases. Given a task dataset, the pipeline uses LLM autoraters to generate candidate bias concepts. It then tests each concept on progressively larger input samples by generating positive and negative variations, and applies statistical techniques for multiple testing and early stopping. A concept is flagged as an unverbalized bias if it yields statistically significant performance differences while not being cited as justification in the model's CoTs. We evaluate our pipeline across seven LLMs on three decision tasks (hiring, loan approval, and university admissions). Our technique automatically discovers previously unknown biases in these models (e.g., Spanish fluency, English proficiency, writing formality). In the same run, the pipeline also validates biases that were manually identified by prior work (gender, race, religion, ethnicity). More broadly, our proposed approach provides a practical, scalable path to automatic, more efficient, and broader task-specific unverbalized bias discovery.

For agents

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

get_harvested_code_for_paper("2602.10117")
get_code_for_paper("2602.10117")
have("2602.10117")

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

curl https://syntology.ai/api/ran/2602.10117.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.10117.svg)](https://syntology.ai/paper/2602.10117)

Connect an agent — have() is free.