English
Related papers

Related papers: InfFeed: Influence Functions as a Feedback to Impr…

200 papers

In Reinforcement Learning from Human Feedback (RLHF), it is crucial to learn suitable reward models from human feedback to align large language models (LLMs) with human intentions. However, human feedback can often be noisy, inconsistent,…

Artificial Intelligence · Computer Science 2025-09-03 Taywon Min , Haeone Lee , Yongchan Kwon , Kimin Lee

The goal of data attribution is to trace the model's predictions through the learning algorithm and back to its training data. thereby identifying the most influential training samples and understanding how the model's behavior leads to…

Machine Learning · Computer Science 2025-08-12 Hongbo Zhu , Angelo Cangelosi

Influence functions (IFs) elucidate how training data changes model behavior. However, the increasing size and non-convexity in large-scale models make IFs inaccurate. We suspect that the fragility comes from the first-order approximation…

Machine Learning · Computer Science 2024-05-07 Hyeonsu Lyu , Jonggyu Jang , Sehyun Ryu , Hyun Jong Yang

Language models are commonly fine-tuned via reinforcement learning to alter their behavior or elicit new capabilities. Datasets used for these purposes, and particularly human preference datasets, are often noisy. The relatively small size…

Machine Learning · Computer Science 2025-07-22 Daniel Fein , Gabriela Aranguiz-Dias

Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework, Infusion, uses scalable influence-function approximations to…

Machine Learning · Computer Science 2026-04-09 J Rosser , Robert Kirk , Edward Grefenstette , Jakob Foerster , Laura Ruis

Modern deep learning models for NLP are notoriously opaque. This has motivated the development of methods for interpreting such models, e.g., via gradient-based saliency maps or the visualization of attention weights. Such approaches aim to…

Computation and Language · Computer Science 2020-05-15 Xiaochuang Han , Byron C. Wallace , Yulia Tsvetkov

Many language tasks (e.g., Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling) are naturally framed as sequence tagging problems. However, there has been comparatively little work on interpretability methods for…

Computation and Language · Computer Science 2022-10-26 Sarthak Jain , Varun Manjunatha , Byron C. Wallace , Ani Nenkova

Customer feedback can be an important signal for improving commercial machine translation systems. One solution for fixing specific translation errors is to remove the related erroneous training instances followed by re-training of the…

Computation and Language · Computer Science 2022-10-25 Tsz Kin Lam , Eva Hasler , Felix Hieber

Influence functions approximate the "influences" of training data-points for test predictions and have a wide variety of applications. Despite the popularity, their computational cost does not scale well with model and training data size.…

Machine Learning · Computer Science 2021-09-13 Han Guo , Nazneen Fatema Rajani , Peter Hase , Mohit Bansal , Caiming Xiong

How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data,…

Machine Learning · Statistics 2021-01-01 Pang Wei Koh , Percy Liang

Facial attribute classification relies on large-scale annotated datasets in which many traits, such as age and expression, are inherently ambiguous and continuous but are discretized into categorical labels. Annotation inconsistencies arise…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Basudha Pal , Rama Chellappa

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

Machine Learning · Computer Science 2026-02-02 Jiawei Li

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

In-context learning is a promising paradigm that utilizes in-context examples as prompts for the predictions of large language models. These prompts are crucial for achieving strong performance. However, since the prompts need to be sampled…

Computation and Language · Computer Science 2025-07-15 Shaokun Zhang , Xiaobo Xia , Zhaoqing Wang , Ling-Hao Chen , Jiale Liu , Qingyun Wu , Tongliang Liu

Influence functions estimate effect of individual data points on predictions of the model on test data and were adapted to deep learning in Koh and Liang [2017]. They have been used for detecting data poisoning, detecting helpful and…

Machine Learning · Computer Science 2022-10-04 Nikunj Saunshi , Arushi Gupta , Mark Braverman , Sanjeev Arora

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

How does the training data affect a model's behavior? This is the question we seek to answer with data attribution. The leading practical approaches to data attribution are based on influence functions (IF). IFs utilize a first-order Taylor…

Machine Learning · Computer Science 2025-09-11 Ittai Rubinstein , Samuel B. Hopkins

We study how training data contributes to the emergence of toxic behaviors in large language models. Most prior work on reducing model toxicity adopts reactive approaches, such as fine-tuning pre-trained (and potentially toxic) models to…

Machine Learning · Computer Science 2025-12-08 Zachary Coalson , Juhan Bae , Nicholas Carlini , Sanghyun Hong

Influence functions provide crucial insights into model training, but existing methods suffer from large computational costs and limited generalization. Particularly, recent works have proposed various metrics and algorithms to calculate…

Machine Learning · Computer Science 2025-10-31 Ishika Agarwal , Dilek Hakkani-Tür

In this work, we focus on the use of influence functions to identify relevant training examples that one might hope "explain" the predictions of a machine learning model. One shortcoming of influence functions is that the training examples…

Machine Learning · Computer Science 2020-03-27 Elnaz Barshan , Marc-Etienne Brunet , Gintare Karolina Dziugaite
‹ Prev 1 2 3 10 Next ›