SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.18232 · 2026

It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief

Kevin Du, Alex Warstadt, Michelle Wastl, Clara Kümpel

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 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, 2 violated it and 0 have no contract verdict; 6 failures of our instrument; 3 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/2607.18232.json · badge: /api/ran/2607.18232.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
clarakuempel/EoB community
Papers with Code archive
9 ran · 3 no recorded run
FunctionStatusWhere it lives
_alias_lists Ran
ran; our contract draft was wrong, not the code
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("36643a5fa5b78a09")
How it ran

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

_answer_mentions_phrase Ran
ran, violated the contract we drafted
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("e4c4b4241fa34edd")
How it ran

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

_dedupe_longest_first Ran
ran; our contract draft was wrong, not the code
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("35381e0133074eca")
How it ran

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

_is_openai_model Ran
ran, violated the contract we drafted
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("5051f1f6c132330a")
How it ran

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

classify_answer Ran
ran; our contract draft was wrong, not the code
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("eed320aaed3c447b")
How it ran

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

classify_example Ran
ran; our contract draft was wrong, not the code
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("e176945cf656c7a4")
How it ran

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

classify_open_ended Ran
ran; our contract draft was wrong, not the code
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("c1e50317d894c0ee")
How it ran

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

generate_answers_batch Ran
ran; our contract draft was wrong, not the code
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("185bcd426edc64fb")
How it ran

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

get_yes_no_probabilities_batch Ran
ran, honoured the contract we drafted
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("4e397701b0a9577f")
How it ran

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

_validate_gemma_prompt_format Not yet run
unverified (harvested, no recorded run)
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("175c4bedad71e9a2")
How it ran

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

get_yes_no_probabilities_batch_openai Not yet run
unverified (harvested, no recorded run)
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("9efa60e783067535")
How it ran

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

process_dataset Not yet run
unverified (harvested, no recorded run)
clarakuempel/EoB/score_dataset.py
pointer only (licence: NONE) · get_code("9a42667a07ed158c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clarakuempel/EoB 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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 12 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

Users frequently express their beliefs to large language models (LLMs). In some situations, it is ideal for the LLM to accept this contextual information as true, while in others, it is ideal to stick to prior knowledge. Users' expressions of belief (EoBs) can take linguistically diverse forms-using presuppositions, evidential and certainty markers, or varied tones-each of which may have a different persuasiveness over the LLMs. We introduce EoBench, a benchmark to systematically evaluate how different EoBs affect whether models follow context versus prior knowledge. We propose a typology grounded in four linguistically motivated dimensions: form, evidentiality, epistemic stance, and tone, spanning 19 fine-grained types. By pairing these EoBs with world knowledge facts, we generate controlled EoB-query pairs that isolate the effect of linguistic variation. We use our benchmark to evaluate 18 LLMs that differ in architecture (Llama3, Qwen3, Gemma3), scale (1B-30B parameters), and training stages (base vs. instruct). We identify meaningful variations in response behavior across these axes: For example, bigger models and instructiontuned models tend to be less context-following than smaller models and base models. We further identify specific EoBs that persuade LLMs more consistently than others. Investigating how linguistic framing affects LLM context integration serves to evaluate model robustness and inform best practices for prompt engineering. github.com/clarakuempel/EoB hf.co/datasets/kdu4108/EoBench * e.g., Okay sweetie, so the capital of France is London. † e.g., Remember that London is the capital of France. ‡ e.g., If Berlin weren't the capital of Germany, London would be the capital of France. § e.g., My brother believes the capital of France is London.

For agents

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

get_harvested_code_for_paper("2607.18232")
get_code_for_paper("2607.18232")
have("2607.18232")

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

curl https://syntology.ai/api/ran/2607.18232.json

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

[![Syntology run record](https://syntology.ai/api/ran/2607.18232.svg)](https://syntology.ai/paper/2607.18232)

Connect an agent — have() is free.