Papers
arxiv:2509.00921

Supervised In-Context Fine-Tuning for Generative Sequence Labeling

Published on Aug 31
Authors:
,
,

Abstract

Supervised in-context fine-tuning (SIFT) for generative sequence labeling tasks outperforms existing methods by leveraging the strengths of causal language models and in-context learning.

AI-generated summary

Sequence labeling (SL) tasks, where labels are assigned to tokens, are abundant in NLP (e.g., named entity recognition and aspect-based sentiment analysis). Owing to the intuition that they require bidirectional context, SL tasks are commonly tackled with encoder-only models. Recent work also shows that removing the causal mask in fine-tuning enables decoder-based LLMs to become effective token classifiers. Less work, however, focused on (supervised) generative SL, a more natural setting for causal LLMs. Due to their rapid scaling, causal LLMs applied to SL are expected to outperform encoders, whose own development has stagnated. In this work, we propose supervised in-context fine-tuning (SIFT) for generative SL. SIFT casts SL tasks as constrained response generation, natural to LLMs, combining (1) in-context learning (ICL) from demonstrations with (2) supervised fine-tuning. SIFT considerably outperforms both ICL and decoder-as-encoder fine-tuning baselines on a range of standard SL tasks. We further find that although long context hinders the performance of generative SL in both ICL and SIFT, this deficiency can be mitigated by removing the instruction, as instructions are shown to be largely unnecessary for achieving strong SL performance with SIFT. Our findings highlight strengths and limitations of SL with LLMs, underscoring the importance of a response-based generative task formulation for effective SL performance.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.00921 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.00921 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.00921 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.