paper-with-me

홈 › Papers

Neologism Learning as a Parameter-Efficient Alternative to Fine-Tuning for Model Steering

2025-12-21 · Sungjoon Park, Varun Ramamurthi, Owen Terry arxiv

In language modeling, neologisms are new tokens trained to represent a concept not already included in a given model's vocabulary. Neologisms can be used to encourage specific behavior in models, for example by appending prompts with "Give me a neologism answer." Behavioral steering can also be achieved through fine-tuning, albeit with more compute and less flexibility: learning a neologism only trains d parameters and allows the user to still access the model's default behavior. We compare the performance of neologism learning against low-rank adaptation (LoRA) fine-tuning, finding that neologisms outperform fine-tuned models under a matched training setup (same data and hyperparameters). We also investigate self-verbalizations of neologisms, and observe that the model will occasionally make up its own new words when asked about a neologism.

📄 PDF Abstract BibTeX arXiv:2512.18551

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Skill Neologisms: Towards Skill-based Continual Learning

2026-05-06 · Antonin Berthon, Nicolas Astorga, Mihaela van der Schaar arxiv

Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable manner is an open problem: fine-tuning and…

Continual Learning

From Weights to Activations: Is Steering the Next Frontier of Adaptation?

2026-04-15 · Simon Ostermann, Daniil Gurgurov, Tanja Baeumel, Michael A. Hedderich 외 arxiv

Post-training adaptation of language models is commonly achieved through parameter updates or input-based methods such as fine-tuning, parameter-efficient adaptation, and prompting. In parallel, a growing body of work mo…

A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering

2024-11-27 · Daniel Scalena, Elisabetta Fersini, Malvina Nissim

Adapting models to a language that was only partially present in the pre-training data requires fine-tuning, which is expensive in terms of both data and computational resources. As an alternative to fine-tuning, we expl…

LoRA for Gender-Inclusive Rewriting and Activation Steering for Counter-Narrative Generation

2026-07-25 · Akhil Rajeev P, Manoj Balaji J arxiv

Gender-inclusive language generation seeks to transform biased text into inclusive alternatives while preserving semantic meaning and contextual coherence. This paper presents the IHLC system for the LT-EDI 2026 Shared T…

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions

2026-02-05 · Yuntai Bao, Xuhong Zhang, Jintao Chen, Ge Su 외 arxiv

Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from fine-tuning, current methods are susceptible to …