English
Related papers

Related papers: Influence Functions for Preference Dataset Pruning

200 papers

Influence functions approximate how removing a training example changes a quantity of interest, called the target function, such as a held-out loss. To estimate the influence of a group of examples, the standard practice is to sum the…

Machine Learning · Computer Science 2026-05-18 Jaeseung Heo , Kyeongheung Yun , Youngbin Choi , Sehyun Hwang , Jungseul Ok , Dongwoo Kim

Instruction-tuning language models has become a crucial step in aligning them for general use. Typically, this process involves extensive training on large datasets, incurring high training costs. In this paper, we introduce a novel…

Computation and Language · Computer Science 2024-02-19 Dheeraj Mekala , Alex Nguyen , Jingbo Shang

Multi-stage training and knowledge transfer, from a large-scale pretraining task to various finetuning tasks, have revolutionized natural language processing and computer vision resulting in state-of-the-art performance improvements. In…

Machine Learning · Computer Science 2020-07-20 Hongge Chen , Si Si , Yang Li , Ciprian Chelba , Sanjiv Kumar , Duane Boning , Cho-Jui Hsieh

Quantifying the impact of training data points is crucial for understanding the outputs of machine learning models and for improving the transparency of the AI pipeline. The influence function is a principled and popular data attribution…

Machine Learning · Computer Science 2024-03-14 Yongchan Kwon , Eric Wu , Kevin Wu , James Zou

Identifying the training datasets that influence a language model's outputs is essential for minimizing the generation of harmful content and enhancing its performance. Ideally, we can measure the influence of each dataset by removing it…

Computation and Language · Computer Science 2024-06-14 Masaru Isonuma , Ivan Titov

There is an increase in the proliferation of online hate commensurate with the rise in the usage of social media. In response, there is also a significant advancement in the creation of automated tools aimed at identifying harmful text…

Computation and Language · Computer Science 2024-06-10 Rabiraj Bandyopadhyay , Dennis Assenmacher , Jose M. Alonso Moral , Claudia Wagner

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Computation and Language · Computer Science 2023-10-03 Tianci Xue , Ziqi Wang , Heng Ji

One of the most effective methods of channel pruning is to trim on the basis of the importance of each neuron. However, measuring the importance of each neuron is an NP-hard problem. Previous works have proposed to trim by considering the…

Machine Learning · Computer Science 2021-12-07 Bilan Lai , Haoran Xiang , Furao Shen

Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…

Computation and Language · Computer Science 2022-04-27 Navid Rezaei , Marek Z. Reformat

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

Machine Learning · Computer Science 2023-01-31 Hongru Yang , Yingbin Liang , Xiaojie Guo , Lingfei Wu , Zhangyang Wang

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…

Computation and Language · Computer Science 2021-10-08 Xiaochuang Han , Yulia Tsvetkov

Understanding the process of learning in neural networks is crucial for improving their performance and interpreting their behavior. This can be approximately understood by asking how a model's output is influenced when we fine-tune on a…

Machine Learning · Computer Science 2024-06-04 Jordan K. Matelsky , Lyle Ungar , Konrad P. Kording

Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random…

Computation and Language · Computer Science 2020-02-19 Jesse Dodge , Gabriel Ilharco , Roy Schwartz , Ali Farhadi , Hannaneh Hajishirzi , Noah Smith

The Influence Function (IF) is a widely used technique for assessing the impact of individual training samples on model predictions. However, existing IF methods often fail to provide reliable influence estimates in deep neural networks,…

Machine Learning · Computer Science 2025-12-02 Xichen Ye , Yifan Wu , Weizhong Zhang , Cheng Jin , Yifan Chen

Pre-trained models have been shown effective in many code intelligence tasks. These models are pre-trained on large-scale unlabeled corpus and then fine-tuned in downstream tasks. However, as the inputs to pre-training and downstream tasks…

Software Engineering · Computer Science 2022-07-26 Chaozheng Wang , Yuanhang Yang , Cuiyun Gao , Yun Peng , Hongyu Zhang , Michael R. Lyu

Instruction tuning aligns the response of large language models (LLMs) with human preferences. Despite such efforts in human--LLM alignment, we find that instruction tuning does not always make LLMs human-like from a cognitive modeling…

Computation and Language · Computer Science 2024-04-16 Tatsuki Kuribayashi , Yohei Oseki , Timothy Baldwin

The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity…

Computation and Language · Computer Science 2024-01-12 Jianwei Li , Qi Lei , Wei Cheng , Dongkuan Xu

Test-time alignment methods offer a promising alternative to fine-tuning by steering the outputs of large language models (LLMs) at inference time with lightweight interventions on their internal representations. Recently, a prominent and…

Computation and Language · Computer Science 2026-04-28 Imranul Ashrafi , Inigo Jauregi Unanue , Massimo Piccardi

Probes trained on model activations can detect undesirable behaviors like deception or biases that are difficult to identify from outputs alone. This makes them useful detectors to identify misbehavior. Furthermore, they are also valuable…

Machine Learning · Computer Science 2025-10-27 Jan Wehner , Mario Fritz

Fine-tuning Large Language Models (LLMs) with downstream data is often considered time-consuming and expensive. Structured pruning methods are primarily employed to improve the inference efficiency of pre-trained models. Meanwhile, they…

Computation and Language · Computer Science 2026-01-28 Wei Huang , Anda Cheng , Yinggui Wang