paper-with-me

홈 › Papers

Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt

2022-10-06 · Seonghyeon Ye, Joel Jang, Doyoung Kim, Yongrae Jo, Minjoon Seo

Enhancing the zero-shot performance of instruction-following models requires heavy computation, either by scaling the total number of training datasets or the model size. In this work, we explore how retrieval of soft prompts obtained through prompt tuning can efficiently assist hard prompts in zero-shot task generalization. Specifically, we train soft prompt embeddings for each prompt through prompt tuning, store the samples of the training instances mapped with the prompt embeddings, and retrieve the corresponding prompt embedding of the training instance closest to the query instance during inference. While only adding 0.007% additional parameters, retrieval of soft prompt enhances the performance of T0 on unseen tasks by outperforming it on 10 out of 11 datasets as well as improving the mean accuracy of T0 on BIG-bench benchmark by 2.39% points. Also, we report an interesting finding that retrieving source embeddings trained on similar answer choice formats is more important than those on similar task types.

📄 PDF Abstract BibTeX arXiv:2210.03029

Code (1)

seonghyeonye/rospr 공식 구현 pytorch

Tasks

Instruction FollowingRetrieval

Similar Papers 제목 키워드 기반

Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning

2024-04-01 · CVPR 2024 1 · Rongjie Li, Yu Wu, Xuming He

Generative vision-language models (VLMs) have shown impressive performance in zero-shot vision-language tasks like image captioning and visual question answering. However, improving their zero-shot reasoning typically re…

Image CaptioningInstruction FollowingLanguage ModelingLanguage Modelling+4

Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation

2024-11-12 · Sonia Raychaudhuri, Duy Ta, Katrina Ashton, Angel X. Chang 외

Large scale scenes such as multifloor homes can be robustly and efficiently mapped with a 3D graph of landmarks estimated jointly with robot poses in a factor graph, a technique commonly used in commercial robots such as…

Instruction FollowingObjectVision-Language Navigation

From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning

2023-04-17 · Qian Liu, Fan Zhou, Zhengbao Jiang, Longxu Dou 외

Fine-tuning language models on tasks with instructions has demonstrated potential in facilitating zero-shot generalization to unseen tasks. In this paper, we introduce a straightforward yet effective method for enhancing…

MMLUZero-shot Generalization

Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering

2023-10-26 · Sukmin Cho, Jeongyeon Seo, Soyeong Jeong, Jong C. Park

Large language models (LLMs) enable zero-shot approaches in open-domain question answering (ODQA), yet with limited advancements as the reader is compared to the retriever. This study aims at the feasibility of a zero-sh…

Answer SelectionNegationOpen-Domain Question AnsweringQuestion Answering

M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning

2024-09-24 · Taowen Wang, Yiyang Liu, James Chenhao Liang, Junhan Zhao 외

Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across variou…

Zero-shot Generalization