大模型
arxiv.org ·
语言推理向量能否增强多模态推理能力？
该 arXiv 论文提出 LIFT（Language-side reasonIng Facilitation and Transfer），一种轻量向量干预方法：将基座 LLM 中带显式推理链的 Reasoner 路径与无推理链的 Solver 路径之间的答案 token 隐状态差定义为 Reasoning Vectors，注入目标 VLM 的语言侧激活，无需重训主干，并支持可学习的向量适配。作者在两个 VLM、六个推理基准上以匹配协议对比来自基座 LLM 与对齐后 VLM 的向量，结果显示 LLM 来源向量持续优于 VLM 来源向量，表明基座 LLM 是恢复推理能力更有效的来源；进一步分析称向量影响的是中间推理行为而非仅改变最终答案。代码将发布。
AI推荐理由 arXiv 预印本，摘要明确给出方法（LIFT：用基座 LLM 与 VLM 的答案 token 隐状态差定义 Reasoning Vectors，注入目标 VLM 语言侧激活，冻结主干）、实验设置（两个 VLM、六个推理基准、匹配协议对比 LLM 与 VLM 来源向量）和结论（LLM 来源向量更优，且影响中间推理行为而非仅改答案）。新信息具体、可验证路径清晰（代码将发布）。局限：仅摘要，无具体数值、无同行评审，'部分恢复'为作者自述，需谨慎对待。
72
正文
Computer Science > Artificial Intelligence
arXiv:2609.31140 (cs)
[Submitted on 25 Sep 2026]
Title:Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?
Authors:Ziyi Wang, Li Li, Aolin Zhou, Yankun Shen, Chonghan Liu, Shuxia Lin, Xu Yang
View a PDF of the paper titled Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?, by Ziyi Wang and 6 other authors
View PDF
HTML (experimental)
Abstract:Most Vision-Language Models (VLMs) are built by extending pretrained Large Language Models (LLMs) with visual modules and multimodal alignment. However, this multimodal scaling often degrades the language-side reasoning ability originally encoded in the base LLM. While the base LLM retains usable reasoning after scaling, the aligned VLM itself cannot reliably access this ability. Therefore, recovering the degraded reasoning capability in VLMs would benefit more from seeking help from the base LLM than from the VLM alone. Motivated by this, we propose LIFT (Language-side reasonIng Facilitation and Transfer), a lightweight vector-intervention method that transfers reasoning capability from the base LLM to the VLM without retraining the backbone. LIFT defines Reasoning Vectors as answer-token hidden-state differences between a Reasoner path with an explicit reasoning trace and a Solver path without it, and injects these vectors into language-side activations of the target VLM. LIFT further supports learnable vector adaptation while keeping the VLM backbone frozen. We evaluate LIFT on two VLMs across six reasoning benchmarks, comparing Reasoning Vectors extracted from the base LLM and from the aligned VLM under matched protocols. Results show that LLM-derived vectors consistently outperform VLM-derived vectors, confirming that the base LLM is a more effective source for recovering reasoning. LIFT partially recovers degraded reasoning through lightweight language-side interventions. Further analyses show that Reasoning Vectors influence intermediate reasoning behavior rather than merely altering final answers. The source code will be released soon.
Comments:
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.31140 [cs.AI]
(or
arXiv:2609.31140v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.31140
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Ziyi Wang [view email]
[v1]
Fri, 25 Sep 2026 11:31:02 UTC (404 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?, by Ziyi Wang and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
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?)
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?)