Paper Detail

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models

Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang, Yun Chen, Peng Li, Jinsong Su, Yang Liu, Guanhua Chen

arxiv Score 11.2

Published 2026-05-02 · First seen 2026-05-05

General AI

Abstract

A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the instruction-tuned model as a passive target that is only involved at the final merging stage, without guiding the training process. We propose GIFT (Guided Fine-Tuning and Transfer), a simple and efficient framework that incorporates guidance from the instruction model into task adaptation. GIFT fine-tunes a low-rank adapter on the pretrained base model using confidence signals derived from the instruction-tuned model. The learned adapter is then merged into the instruction-tuned model, yielding task-specialized models that preserve general instruction-following behavior. We evaluate GIFT on mathematical and knowledge-intensive benchmarks across multiple model families and scales. Results show that GIFT consistently outperforms direct fine-tuning and representative transfer-based baselines, while maintaining robust generalization and favorable test-time scaling behavior.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{ruan2026gift,
  title = {GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models},
  author = {Zhiwen Ruan and Yichao Du and Jianjie Zheng and Longyue Wang and Yun Chen and Peng Li and Jinsong Su and Yang Liu and Guanhua Chen},
  year = {2026},
  abstract = {A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the instruction-tuned model as a passive target that is only involved at the final merging stage, without guiding the training process. We propose GIFT (Guided Fine-Tuning and Transfer), a simple and efficient framework that incorporates guidance from the instruct},
  url = {https://arxiv.org/abs/2605.01256},
  keywords = {cs.CL},
  eprint = {2605.01256},
  archiveprefix = {arXiv},
}

Metadata

{}