English
Related papers

Related papers: Atyaephyra at SemEval-2025 Task 4: Low-Rank Negati…

200 papers

This paper presents the Annif system in the LLMs4Subjects shared task (Subtask 2) at GermEval-2025. The task required creating subject predictions for bibliographic records using large language models, with a special focus on computational…

Computation and Language · Computer Science 2025-08-25 Osma Suominen , Juho Inkinen , Mona Lehtinen

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…

Machine Learning · Computer Science 2025-04-16 Alexander David Goldie , Chris Lu , Matthew Thomas Jackson , Shimon Whiteson , Jakob Nicolaus Foerster

The paper presents a system developed for the SemEval-2019 competition Task 5 hat-Eval Basile et al. (2019) (team name: LU Team) and Task 6 OffensEval Zampieri et al. (2019b) (team name: NLPR@SRPOL), where we achieved 2nd position in…

Computation and Language · Computer Science 2019-04-11 Alessandro Seganti , Helena Sobol , Iryna Orlova , Hannam Kim , Jakub Staniszewski , Tymoteusz Krumholc , Krystian Koziel

This work studies the challenge of aligning large language models (LLMs) with offline preference data. We focus on alignment by Reinforcement Learning from Human Feedback (RLHF) in particular. While popular preference optimization methods…

Machine Learning · Computer Science 2024-06-07 Xiang Ji , Sanjeev Kulkarni , Mengdi Wang , Tengyang Xie

Large language models (LLMs) possess vast knowledge acquired from extensive training corpora, but they often cannot remove specific pieces of information when needed, which makes it hard to handle privacy, bias mitigation, and knowledge…

Machine Learning · Computer Science 2025-12-09 Yezi Liu , Hanning Chen , Wenjun Huang , Yang Ni , Mohsen Imani

This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works remarkably well as…

Machine Learning · Computer Science 2020-06-30 Rasool Fakoor , Pratik Chaudhari , Alexander J. Smola

Motivated by applications in protein function prediction, we consider a challenging supervised classification setting in which positive labels are scarce and there are no explicit negative labels. The learning algorithm must thus select…

Machine Learning · Computer Science 2019-01-28 Marco Frasca , Nicolò Cesa-Bianchi

We study the problem of learning to rank from pairwise preferences, and solve a long-standing open problem that has led to development of many heuristics but no provable results for our particular problem. Given a set $V$ of $n$ elements,…

Data Structures and Algorithms · Computer Science 2011-05-18 Nir Ailon

While orthogonal subspace methods try to mitigate task interference in Continual Learning (CL), they often suffer from energy diffusion across the basis, hindering knowledge compaction and exhausting capacity for future tasks. We observe…

Machine Learning · Computer Science 2026-05-28 Longhua Li , Lei Qi , Qi Tian , Xin Geng

LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We…

Computation and Language · Computer Science 2026-04-03 Zhiyuan Peng , Xuyang Wu , Huaixiao Tou , Yi Fang , Yu Gong

We present a model-based offline reinforcement learning policy performance lower bound that explicitly captures dynamics model misspecification and distribution mismatch and we propose an empirical algorithm for optimal offline policy…

Machine Learning · Computer Science 2023-01-30 Kefan Dong , Yannis Flet-Berliac , Allen Nie , Emma Brunskill

Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilizes self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 John Seon Keun Yi , Minseok Seo , Jongchan Park , Dong-Geol Choi

Neural networks are not learning optimal decision boundaries. We show that decision boundaries are situated in areas of low training data density. They are impacted by few training samples which can easily lead to overfitting. We provide a…

Machine Learning · Computer Science 2023-10-09 Johannes Schneider

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

This paper proposes a new method for solving the well-known rank aggregation problem from pairwise comparisons using the method of low-rank matrix completion. The partial and noisy data of pairwise comparisons is transformed into a matrix…

Machine Learning · Statistics 2018-06-15 Tal Levy , Alireza Vahid , Raja Giryes

Enabling low precision implementations of deep learning models, without considerable performance degradation, is necessary in resource and latency constrained settings. Moreover, exploiting the differences in sensitivity to quantization…

Machine Learning · Computer Science 2022-10-28 Ignacio Hounie , Juan Elenter , Alejandro Ribeiro

Low-rank structures play important role in recent advances of many problems in image science and data science. As a natural extension of low-rank structures for data with nonlinear structures, the concept of the low-dimensional manifold…

Computer Vision and Pattern Recognition · Computer Science 2017-02-10 Rongjie Lai , Jia Li

We show how to incorporate information from labeled examples into nonnegative matrix factorization (NMF), a popular unsupervised learning algorithm for dimensionality reduction. In addition to mapping the data into a space of lower…

Machine Learning · Computer Science 2011-12-19 Youngmin Cho , Lawrence K. Saul

Offline imitation learning (offline IL) enables training effective policies without requiring explicit reward annotations. Recent approaches attempt to estimate rewards for unlabeled datasets using a small set of expert demonstrations.…

Machine Learning · Computer Science 2025-11-19 Shengjie Sun , Jiafei Lyu , Runze Liu , Mengbei Yan , Bo Liu , Deheng Ye , Xiu Li

During pretraining, LLMs inadvertently memorize sensitive or copyrighted data, posing significant compliance challenges under legal frameworks like the GDPR and the EU AI Act. Fulfilling these mandates demands techniques that can remove…

Machine Learning · Computer Science 2026-03-23 Efstratios Zaradoukas , Bardh Prenkaj , Gjergji Kasneci