paper-with-me

Papers

AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking

2025-03-04 · Iraklis Premptis, Maria Lymperaiou, Giorgos Filandrianos, Orfeas Menis Mastromichalakis, Athanasios Voulodimos, Giorgos Stamou

The Unlearning Sensitive Content from Large Language Models task aims to remove targeted datapoints from trained models while minimally affecting their general knowledge. In our work, we leverage parameter-efficient, gradient-based unlearning using low-rank (LoRA) adaptation and layer-focused fine-tuning. To further enhance unlearning effectiveness, we employ data chunking, splitting forget data into disjoint partitions and merging them with cyclically sampled retain samples at a pre-defined ratio. Our task-agnostic method achieves an outstanding forget-retain balance, ranking first on leaderboards and significantly outperforming baselines and competing systems.

📄 PDF Abstract BibTeX arXiv:2503.02443

Code (0)

등록된 구현이 없습니다.

Tasks

ChunkingGeneral Knowledge

Similar Papers 제목 키워드 기반

AILS-NTUA at SemEval-2026 Task 3: Efficient Dimensional Aspect-Based Sentiment Analysis

2026-03-05 · Stavros Gazetas, Giorgos Filandrianos, Maria Lymperaiou, Paraskevi Tzouveli 외 arxiv

In this paper, we present AILS-NTUA system for Track-A of SemEval-2026 Task 3 on Dimensional Aspect-Based Sentiment Analysis (DimABSA), which encompasses three complementary problems: Dimensional Aspect Sentiment Regress…

Aspect Sentiment Triplet ExtractionSentiment Analysis

AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations

2026-03-11 · Dimosthenis Athanasiou, Maria Lymperaiou, Giorgos Filandrianos, Athanasios Voulodimos 외 arxiv

We present the AILS-NTUA system for SemEval-2026 Task 8 (MTRAGEval), addressing all three subtasks of multi-turn retrieval-augmented generation: passage retrieval (A), reference-grounded response generation (B), and end-…

Response GenerationPassage Retrieval

NTUAAILS at SemEval-2020 Task 11: Propaganda Detection and Classification with biLSTMs and ELMo

2020-12-01 · SEMEVAL 2020 · Anastasios Arsenos, Georgios Siolas

This paper describes the NTUAAILS submission for SemEval 2020 Task 11 Detection of Propaganda Techniques in News Articles. This task comprises of two different sub-tasks, namely A: Span Identification (SI), B: Technique …

ArticlesPropaganda detectionWord Embeddings

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

2025-03-27 · Haoming Xu, Shuxun Wang, Yanqiu Zhao, Yi Zhong 외

This paper presents the ZJUKLAB team's submission for SemEval-2025 Task 4: Unlearning Sensitive Content from Large Language Models. This task aims to selectively erase sensitive knowledge from large language models, avoi…

iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss

2025-07-22 · Yujian Sun, Tian Li arxiv

As the Large Language Model (LLM) gains widespread adoption, increasing attention has been given to the challenge of making LLM forget non-compliant data memorized during its pre-training. Machine Unlearning focuses on e…