English
Related papers

Related papers: Improving Instruct Models for Free: A Study on Par…

200 papers

Instruction Tuning has emerged as a pivotal post-training paradigm that enables pre-trained language models to better follow user instructions. Despite its significance, little attention has been given to optimizing the loss function used.…

Computation and Language · Computer Science 2025-07-16 Anwoy Chatterjee , H S V N S Kowndinya Renduchintala , Sumit Bhatia , Tanmoy Chakraborty

In this work, we explore "prompt tuning", a simple yet effective mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts…

Computation and Language · Computer Science 2021-09-03 Brian Lester , Rami Al-Rfou , Noah Constant

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a…

Computation and Language · Computer Science 2024-05-22 Uri Shaham , Jonathan Herzig , Roee Aharoni , Idan Szpektor , Reut Tsarfaty , Matan Eyal

Recently, a boom of papers has shown extraordinary progress in zero-shot and few-shot learning with various prompt-based models. It is commonly argued that prompts help models to learn faster in the same way that humans learn faster when…

Computation and Language · Computer Science 2022-04-22 Albert Webson , Ellie Pavlick

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

Computation and Language · Computer Science 2023-02-10 Joel Jang , Seungone Kim , Seonghyeon Ye , Doyoung Kim , Lajanugen Logeswaran , Moontae Lee , Kyungjae Lee , Minjoon Seo

The Superficial Alignment Hypothesis posits that almost all of a language model's abilities and knowledge are learned during pre-training, while post-training is about giving a model the right style and format. We re-examine these claims by…

Computation and Language · Computer Science 2024-10-08 Mohit Raghavendra , Vaskar Nath , Sean Hendryx

Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding…

Machine Learning · Computer Science 2023-12-29 Aditi Jha , Sam Havens , Jeremy Dohmann , Alex Trott , Jacob Portes

Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training.…

Computation and Language · Computer Science 2021-09-08 Kaixin Ma , Filip Ilievski , Jonathan Francis , Satoru Ozaki , Eric Nyberg , Alessandro Oltramari

Large language models (LLMs) consistently benefit from further fine-tuning on various tasks. However, we observe that directly tuning the Instruct (i.e., instruction-tuned) models often leads to marginal improvements and even performance…

Computation and Language · Computer Science 2025-09-29 Taiqiang Wu , Runming Yang , Jiayi Li , Pengfei Hu , Yik-Chung Wu , Ngai Wong , Yujiu Yang

Prompting Large Language Models (LLMs), or providing context on the expected model of operation, is an effective way to steer the outputs of such models to satisfy human desiderata after they have been trained. But in rapidly evolving…

Machine Learning · Computer Science 2025-08-08 Younwoo Choi , Muhammad Adil Asif , Ziwen Han , John Willes , Rahul G. Krishnan

Pre-trained Large Language Models (LLMs) require post-training methods such as supervised fine-tuning (SFT) on instruction-response pairs to enable instruction following. However, this process can potentially harm existing capabilities…

Computation and Language · Computer Science 2025-02-04 Yihan Wang , Andrew Bai , Nanyun Peng , Cho-Jui Hsieh

Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an instruction data selection framework based on weighted in-context influence (wICI),…

Computation and Language · Computer Science 2026-04-29 Guangzeng Han , Xiaolei Huang

The development of large language models leads to the formation of a pre-train-then-align paradigm, in which the model is typically pre-trained on a large text corpus and undergoes a tuning stage to align the model with human preference or…

Computation and Language · Computer Science 2025-03-19 Kaiser Sun , Mark Dredze

Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We propose to combine…

Computation and Language · Computer Science 2022-12-22 Yukun Huang , Yanda Chen , Zhou Yu , Kathleen McKeown

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…

Computation and Language · Computer Science 2026-05-05 Zhiwen Ruan , Yichao Du , Jianjie Zheng , Longyue Wang , Yun Chen , Peng Li , Jinsong Su , Yang Liu , Guanhua Chen

This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially…

Computation and Language · Computer Science 2022-02-10 Jason Wei , Maarten Bosma , Vincent Y. Zhao , Kelvin Guu , Adams Wei Yu , Brian Lester , Nan Du , Andrew M. Dai , Quoc V. Le

Modern language models (LMs) need to follow human instructions while being faithful; yet, they often fail to achieve both. Here, we provide concrete evidence of a trade-off between instruction following (i.e., follow open-ended…

Computation and Language · Computer Science 2024-08-01 Zhengxuan Wu , Yuhao Zhang , Peng Qi , Yumo Xu , Rujun Han , Yian Zhang , Jifan Chen , Bonan Min , Zhiheng Huang

Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-context learning with large language models struggles on tasks where models must integrate…

Computation and Language · Computer Science 2026-04-21 Iqra Ali , Talia Tseriotou , Mahmud Elahi Akhter , Yuxiang Zhou , Maria Liakata

Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context…

Computation and Language · Computer Science 2024-10-23 Tsachi Blau , Moshe Kimhi , Yonatan Belinkov , Alexander Bronstein , Chaim Baskin

Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically…

Computation and Language · Computer Science 2024-02-01 Pinzhen Chen , Shaoxiong Ji , Nikolay Bogoychev , Andrey Kutuzov , Barry Haddow , Kenneth Heafield