AI News HubLIVE
原文2 min read

Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models

A new study investigates how discourse-role labels such as 'Reference:', 'Instruction:', and 'Example:' affect language models' reliance on context. Using a paired fixed-content probe on 500 MMLU-Pro items, the researchers found that labels can shift misleading adoption rates by 56-84 percentage points. Labels like Instruction and Reference increase adoption, while Example suppresses it. The study recommends that RAG benchmarks report and control wrapper labels.

SourcearXiv Computational LinguisticsAuthor: Jianguo Zhu

[2606.04109] Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models

[Submitted on 2 Jun 2026]

Title:Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models

View a PDF of the paper titled Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models, by Jianguo Zhu

View PDF HTML (experimental)

Abstract:Context-augmented language model systems often wrap supplied content with labels such as Reference:, Evidence:, Instruction:, Note:, or Example:, but the effect of these labels on reader-model behavior remains underexplored. We introduce a paired fixed-content probe over 500 MMLU-Pro items: each item receives the same misleading answer-bearing assertion under different discourse-role labels, and adoption is measured by whether the model outputs the injected wrong option. Across GPT-5.5, DeepSeek V4 Pro, Llama-3-8B-Instruct, and Qwen2.5-7B-Instruct, Misleading Adoption Rate shifts by 56-84 percentage points. Binding or source-like labels such as Instruction: and Reference: produce high adoption, whereas Example: consistently suppresses it. Paired tests, bootstrap intervals, final-instruction ablations, and Qwen final-step log-probability probes support a label-conditioned candidate preference. Boundary probes show where the effect weakens or persists: arithmetic tasks reduce adoption, passage-shaped external context preserves smaller label gaps, short-answer evaluation rules out option-letter copying, and nested-label conflicts suggest that illustrative framing can delimit adoption scope. A 200-case single-author manual audit confirms that the short-answer contrasts are stable under conservative adjudication. The resulting claim is bounded but practical: context-utilization and reader-side RAG benchmarks should report and control wrapper labels, because presentation choices can change measured reliance on supplied context.

Comments: Preprint. 1 figure, 9 tables

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2606.04109 [cs.CL]

(or arXiv:2606.04109v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.04109

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: JianGuo Zhu [view email] [v1] Tue, 2 Jun 2026 18:12:57 UTC (55 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models, by Jianguo Zhu

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)