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

• URL: http://arxiv.org/abs/2507.16263v1
• Date: Tue, 22 Jul 2025 06:21:54 GMT
• Title: iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss
• Authors: Yujian Sun, Tian Li,
• Abstract summary: Machine Unlearning focuses on efficiently erasing sensitive information from Large Language Models.<n>In this work, we propose a more controllable forgetting loss, Effective Unlearning Loss.<n>Our system ranked 5th on the competition leaderboard.
• Score: 6.77698376992826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 efficiently erasing sensitive information from LLM under limited computational resources. To advance research in this area, SemEval 2025 Task 4: "Unlearning Sensitive Content from Large Language Models" introduces three unlearning datasets and establishes a benchmark by evaluating both forgetting effectiveness and the preservation of standard capabilities. In this work, we propose a more controllable forgetting loss, Effective Unlearning Loss, and explore its integration with various techniques to achieve more efficient and controlled unlearning. Our system ultimately ranked 5th on the competition leaderboard.

Related papers

• Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness [30.596695293390415]
  Interpolated Approximate Measurement (IAM) is a framework designed for unlearning inference.<n>IAM quantifies sample-level unlearning completeness by interpolating the model's generalization-fitting behavior gap on queried samples.<n>We apply IAM to recent approximate unlearning algorithms, revealing general risks of both over-unlearning and under-unlearning.
  arXiv  Detail & Related papers  (2025-06-06T14:22:18Z)
• Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs [49.1574468325115]
  This paper describes LIBU (LoRA enhanced influence-based unlearning), an algorithm to solve the task of unlearning.<n>The algorithm combines classical textitinfluence functions to remove the influence of the data from the model and textitsecond-order optimization to stabilize the overall utility.
  arXiv  Detail & Related papers  (2025-06-04T15:10:09Z)
• Does Machine Unlearning Truly Remove Model Knowledge? A Framework for Auditing Unlearning in LLMs [58.24692529185971]
  We introduce a comprehensive auditing framework for unlearning evaluation comprising three benchmark datasets, six unlearning algorithms, and five prompt-based auditing methods.<n>We evaluate the effectiveness and robustness of different unlearning strategies.
  arXiv  Detail & Related papers  (2025-05-29T09:19:07Z)
• AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking [5.535042121804845]
  We leverage parameter-efficient, gradient-based unlearning using low-rank adaptation and layer-focused fine-tuning.<n>We employ data chunking, splitting forget data into disjoint partitions and merging them with cyclically sampled retain samples at a pre-defined ratio.
  arXiv  Detail & Related papers  (2025-03-04T09:39:09Z)
• Cyber for AI at SemEval-2025 Task 4: Forgotten but Not Lost: The Balancing Act of Selective Unlearning in Large Language Models [0.0]
  Large Language Models (LLMs) face challenges in maintaining privacy, ethics, and compliance.<n>Retraining these models from scratch is computationally infeasible.<n>This work focuses on the application of selective unlearning in LLMs to address this challenge.
  arXiv  Detail & Related papers  (2025-03-02T07:58:08Z)
• A Closer Look at Machine Unlearning for Large Language Models [46.245404272612795]
  Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns.<n>We discuss several issues in machine unlearning for LLMs and provide our insights on possible approaches.
  arXiv  Detail & Related papers  (2024-10-10T16:56:05Z)
• Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models [52.03511469562013]
  We introduce the Iterative Contrastive Unlearning (ICU) framework, which consists of three core components.<n>A Knowledge Unlearning Induction module targets specific knowledge for removal using an unlearning loss.<n>A Contrastive Learning Enhancement module preserves the model's expressive capabilities against the pure unlearning goal.<n>An Iterative Unlearning Refinement module dynamically adjusts the unlearning process through ongoing evaluation and updates.
  arXiv  Detail & Related papers  (2024-07-25T07:09:35Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Rethinking Machine Unlearning for Large Language Models [85.92660644100582]
  We explore machine unlearning in the domain of large language models (LLMs)<n>This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities.
  arXiv  Detail & Related papers  (2024-02-13T20:51:58Z)
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
  Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data. This process might suffer from privacy issues and violations of data protection regulations. We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
  arXiv  Detail & Related papers  (2023-10-31T03:35:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.