paper-with-me

홈 › Papers

Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications

2023-10-21 · Manuel Faysse, Gautier Viaud, Céline Hudelot, Pierre Colombo

Instruction Fine-Tuning (IFT) is a powerful paradigm that strengthens the zero-shot capabilities of Large Language Models (LLMs), but in doing so induces new evaluation metric requirements. We show LLM-based metrics to be well adapted to these requirements, and leverage them to conduct an investigation of task-specialization strategies, quantifying the trade-offs that emerge in practical industrial settings. Our findings offer practitioners actionable insights for real-world IFT model deployment.

📄 PDF Abstract BibTeX arXiv:2310.14103

Code (1)

manuelfay/ifteval 공식 구현

Similar Papers 제목 키워드 기반

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

2026-05-02 · Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang 외 arxiv

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 …

Retriv at BLP-2025 Task 2: Test-Driven Feedback-Guided Framework for Bangla-to-Python Code Generation

2025-11-10 · K M Nafi Asib, Sourav Saha, Mohammed Moshiul Hoque arxiv

Large Language Models (LLMs) have advanced the automated generation of code from natural language prompts. However, low-resource languages (LRLs) like Bangla remain underrepresented due to the limited availability of ins…

Code Generation

Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering

2023-07-31 · Vaibhav Adlakha, Parishad BehnamGhader, Xing Han Lu, Nicholas Meade 외

Retriever-augmented instruction-following models are attractive alternatives to fine-tuned approaches for information-seeking tasks such as question answering (QA). By simply prepending retrieved documents in its input a…

Instruction FollowingQuestion Answering

Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning

2025-02-26 · Hongyi Cal, Jie Li, Wenzhen Dong

The effectiveness of instruction fine-tuning for Large Language Models is fundamentally constrained by the quality and efficiency of training datasets. This work introduces Low-Confidence Gold (LCG), a novel filtering fr…

Diversity

How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

2023-06-07 · NeurIPS 2023 11 · Yizhong Wang, Hamish Ivison, Pradeep Dasigi, Jack Hessel 외

In this work we explore recent advances in instruction-tuning language models on a range of open instruction-following datasets. Despite recent claims that open models can be on par with state-of-the-art proprietary mode…

Instruction Following