arXiv Machine Learning September 3, 2026 By Liam Byrne, David Dylan, Orla Fitzgerald, Eoin Doyle, Ciara Nolan, Padraig Lynch, Sinead Gallagher

Prompt-Space Meta-Learning Does Not Transfer Across Users: A Frozen-LLM Negative Result

Read the original on arXiv Machine Learning →

The paper investigates whether a frozen large language model can be personalized to individual users via prompt-space meta‑learning. Using the Muse framework, the authors evolve a shared adaptation prompt across a meta‑train user population and test it zero‑shot on over 200 held‑out users in two personalization benchmarks (LaMP‑2 and LaMP‑3). The results show that Muse does not outperform its un‑evolved seed prompt or a control that trains on mismatched user‑support pairs, and it is outperformed by simple few‑shot retrieval on the rating task. The authors attribute this failure to a meta‑objective collapse, where the validation objective is invariant to genuine user‑support correspondence, leading to over‑optimization of instruction polish rather than transferable adaptation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 1

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

arXiv:2606. 32032v1 Announce Type: cross Abstract: Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes.

By Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona, Idan Szpektor, Arman Cohan

llms reinforcement-learning benchmarks safety

arXiv AI

Aug 11

Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning

arXiv:2608. 09507v1 Announce Type: cross Abstract: Natural language user preferences provide an interpretable interface for LLM personalization.

By Yuting Liu, Wei Wu, Jianzhe Zhao, Guibing Guo

llms rag agents reinforcement-learning

arXiv AI

Sep 21

One Prompt Does Not Fit All: Self-Meta-Evolve for Personalized Information Extraction

arXiv:2609.21626v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for enterprise information extraction (IE), where the same document must be reorganized differen...

By Hongliang Li, Lu Wang, Yong Xu, Hanyang Chen, Zhitao Hou, Xiaoting Qin, Song Ge, Qingwei Lin, Dongmei Zhang

llms benchmarks

arXiv AI

Aug 11

Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models

arXiv:2608. 09109v1 Announce Type: new Abstract: User feedback offers natural supervision for persistent LLM improvement, but a single message may support multiple behavioral changes with different scopes of generalization.

By Xuanchen Li, Haitao Li, Yujia Zhou, Qingyi Pan, Heng Wang, Yiqun Liu, Min Zhang, Qingyao Ai

llms fine-tuning efficiency

arXiv AI

Aug 11

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models

arXiv:2608. 08829v1 Announce Type: cross Abstract: Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the injection layers globally per task.

By Muhammad Faishal Adly Nelwan, Alfan Farizki Wicaksono

llms rag safety

Hugging Face Trending Papers

Aug 3

FLARE: Few-shot Learning-based Adaptive Reflective Engine

Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-of-the-art optimizers like GEPA (Genetic-Pareto) have argued that reflective instruction evolution can outperform traditional reinforcement learning and few-shot optimization.

llms rag agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning

One Prompt Does Not Fit All: Self-Meta-Evolve for Personalized Information Extraction

Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models

FLARE: Few-shot Learning-based Adaptive Reflective Engine