大模型
arxiv.org ·
超强机器学习：LLM 生成的解释尚不足以教会人类主动学习策略
该论文将归纳逻辑编程（ILP）与 LLM 结合，构建自动生成并评分解释的流水线，以替代此前需专家逐领域手工编写的解释模板。研究在三个相关领域开展人类教学试验，检验这些解释能否让人类习得可跨领域迁移的主动学习策略。探索性结果显示：简洁的专家撰写解释对初始表现较高的学习者有益，而流水线生成的解释相对自学没有优势，尽管 LLM-as-judge 评价认为其质量更高。作者据此指出 LLM 质量指标与人类学习结果之间存在系统性差距，解释复杂度相对任务难度是关键因素，并呼吁以人类认知约束而非 LLM 偏好来设计解释方法与评估标准。
AI推荐理由 arXiv 论文（v3，2026-09-22 修订），作者来自班贝格大学与帝国理工，方法为 ILP 结合 LLM 自动生成并评分解释，并在三个相关领域的人类教学试验中检验。核心新信息是：LLM-as-judge 评分更高的自动生成解释，在人类学习迁移上并未优于自学，而简洁的专家撰写解释对初始表现较高的学习者有帮助，揭示 LLM 质量指标无法预测人类学习效果，并指出解释复杂度与任务难度的匹配是关键因素。局限是探索性结果、样本与领域有限，结论为初步性质，不能推广为普遍定论。
78
正文
Computer Science > Artificial Intelligence
arXiv:2509.00961 (cs)
[Submitted on 31 Aug 2025 (v1), last revised 22 Sep 2026 (this version, v3)]
Title:Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy
Authors:Lun Ai, Johannes Langer, Ute Schmid, Stephen Muggleton
View a PDF of the paper titled Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy, by Lun Ai and 3 other authors
View PDF
HTML (experimental)
Abstract:Active learning is a general learning mechanism shared by artificial and human learners. Whether AI can teach humans such a strategy that transfers across domains is an open question. Ultra Strong Machine Learning (USML), a system whose explanations quantifiably improve human out-of-sample performance compared to self-learning, is uniquely positioned to answer this question. Prior USML work relied on hand-crafted explanation templates that require expert effort for each new domain and do not scale. We developed an explanation pipeline combining Inductive Logic Programming (ILP) with large language models (LLMs) to automate explanation generation and scoring. We tested whether these explanations achieve USML in a human trial teaching active learning strategies across three related domains. Our exploratory results show that concise, expert-written explanations benefit learners with higher initial performance, while pipeline-generated explanations provide no advantage over self-learning despite being rated as higher quality from an LLM-as-judge evaluation. This case study reveals a systematic gap that LLM quality metrics do not predict human learning outcomes. Our findings point to explanation complexity relative to task difficulty as a key factor, and call for explanation methods and evaluation criteria grounded in human cognitive constraints rather than LLM preference.
Subjects:
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:
arXiv:2509.00961 [cs.AI]
(or
arXiv:2509.00961v3 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2509.00961
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Lun Ai [view email]
[v1]
Sun, 31 Aug 2025 19:04:31 UTC (1,524 KB)
[v2]
Tue, 27 Jan 2026 17:01:53 UTC (1,519 KB)
[v3]
Tue, 22 Sep 2026 13:31:21 UTC (1,500 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy, by Lun Ai and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2025-09
Change to browse by:
cs
cs.LG
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?)