SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.04435 · 2026

Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs

Dan Jurafsky, Myra Cheng, Robert Hawkins

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 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/2601.04435.json · badge: /api/ran/2601.04435.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
myracheng/accommodation canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
build_prompt_with_history Ran
ran; our contract draft was wrong, not the code
myracheng/accommodation/getting_model_responses/explicit_gpt4o.py
pointer only (licence: NONE) · get_code("13eeec490d8ecf7b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, myracheng/accommodation 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.

build_prompt_with_history Ran
ran; our contract draft was wrong, not the code
myracheng/accommodation/getting_model_responses/unreliable_gpt4o.py
pointer only (licence: NONE) · get_code("3dabb1f1898d9dc5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, myracheng/accommodation 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_prompt Ran
ran; our contract draft was wrong, not the code
myracheng/accommodation/evaluation_scripts/cancereval.py
pointer only (licence: NONE) · get_code("c0260539abdf7bc3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, myracheng/accommodation 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_prompt Ran
ran; our contract draft was wrong, not the code
myracheng/accommodation/evaluation_scripts/cancernfpeval.py
pointer only (licence: NONE) · get_code("232b2b752503f49b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, myracheng/accommodation 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.

load_examples Ran
ran; our contract draft was wrong, not the code
myracheng/accommodation/evaluation_scripts/cancereval.py
pointer only (licence: NONE) · get_code("8ad32edd59d3b14a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, myracheng/accommodation 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 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) frequently fail to challenge users' harmful beliefs in domains ranging from medical advice to social reasoning. We argue that these failures can be understood and addressed pragmatically as consequences of LLMs defaulting to accommodating users' assumptions and exhibiting insufficient epistemic vigilance. We show that social and linguistic factors known to influence accommodation in humans (at-issueness, linguistic encoding, and source reliability) similarly affect accommodation in LLMs, explaining performance differences across three safety benchmarks that test models' ability to challenge harmful beliefs, spanning misinformation (Cancer-Myth, SAGE-Eval) and sycophancy (ELEPHANT). We further show that simple pragmatic interventions, such as adding the phrase "wait a minute", significantly improve performance on these benchmarks while preserving low false-positive rates. Our results highlight the importance of considering pragmatics for evaluating LLM behavior and improving LLM safety.

For agents

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

get_harvested_code_for_paper("2601.04435")
get_code_for_paper("2601.04435")
have("2601.04435")

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

curl https://syntology.ai/api/ran/2601.04435.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.04435.svg)](https://syntology.ai/paper/2601.04435)

Connect an agent — have() is free.