"言語モデルとして": チャットテンプレートがLLMの自己参照的な発言を切り替える
"As a Language Model": Chat Template Switches LLM Self-Referential Voice (arxiv.org)
要約
本研究では、大規模言語モデル(LLM)が自己言及的な質問に対して「私はAIです」といった免責事項を発する際、チャットテンプレートの有無がその発言スタイルを大きく左右することを明らかにしました。チャットテンプレートが存在すると免責事項が増え、存在しないと自己言及的な発言が増加します。さらに、モデルの活性化空間にこの行動を制御する方向性を見出し、LLMの自己認識に関する研究における潜在的な交絡因子を指摘しています。
全文翻訳
Computer Science > Machine Learning
arXiv:2609.25021 (cs)
[Submitted on 9 Aug 2026]
Title:"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It
Authors:Jędrzej Maczan
View a PDF of the paper titled "As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It, by J\k{e}drzej Maczan
Abstract:Large Language Models (LLMs) tend to add disclaimers like "I'm just an AI" when asked about something related to themselves. The self-reports from such responses are used in debates about AI safety or self-knowledge of the models, yet what drives them is not well understood. Are the models telling us about themselves or rather how they are deployed? In this work, we show that the chat template works like a switch - when present, it turns this disclaimer voice up and experiential voice like "I feel" down, across 8 popular open-source instruct models up to 9B parameters in size. And conversely when the chat template is not present, it turns the disclaimer voice down and experiential voice up. Inside the activations of 3 models, we find a direction that steers this behavior. Removing the direction in the model's activation space turns disclaimer voice down and adding it turns it up, while a random direction of the same size has little effect. We find that instruct models without chat template, when we add the disclaimer direction to them, disclaim like the template was there. Since the chat template controls the disclaimer voice of LLMs, then researchers studying self-reports or introspection of models might have a confound they need to control for. Our results show that there is a direction they can use to steer this voice. More broadly, our work shows that what models say about themselves is not a fact about them. What they say doesn't come only from weights, but it is partially set by the chat template, and because of that a model's self-description shouldn't be treated literally.
| Comments: | Accepted to COLM 2026 Workshop on Efficient Reasoning and KONVENS 2026 First Workshop on Evaluating LLMs for Specialized Domains (Eval4SD) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.25021 [cs.LG] |
| (or arXiv:2609.25021v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.25021 arXiv-issued DOI via DataCite |
Submission history
From: Jędrzej Maczan [view email]
[v1] Sun, 9 Aug 2026 18:38:58 UTC (139 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled "As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It, by J\k{e}drzej Maczan
[画像: license icon] view license
Additional Features
Current browse context:
cs.LG
Change to browse by:
References & Citations
Loading...
BibTeX formatted citation
loading...
Data provided by:
Bookmark
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?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
- 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?)