Related papers: EMSEdit: Efficient Multi-Step Meta-Learning-based …

A promising way to improve the sample efficiency of reinforcement learning is model-based methods, in which many explorations and evaluations can happen in the learned models to save real-world samples. However, when the learned model has a…

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…

Masked diffusion language models enable parallel token generation and offer improved decoding efficiency over autoregressive models. However, their performance degrades significantly when generating multiple tokens simultaneously, due to a…

Large language models store not only isolated facts but also rules that support reasoning across symbolic expressions, natural language explanations, and concrete instances. Yet most model editing methods are built for fact-level knowledge,…

Knowledge Editing (KE) aims to correct and update factual information in Large Language Models (LLMs) to ensure accuracy and relevance without computationally expensive fine-tuning. Though it has been proven effective in several domains,…

Knowledge editing methods (KEs) are a cost-effective way to update the factual content of large language models (LLMs), but they pose a dual-use risk. While KEs are beneficial for updating outdated or incorrect information, they can be…

Text embeddings are typically evaluated on a limited set of tasks, which are constrained by language, domain, and task diversity. To address these limitations and provide a more comprehensive evaluation, we introduce the Massive…

Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenarios where edits must…

Large Language Models (LLMs) have demonstrated remarkable efficacy in text embedding, yet current adaptation methods like LoRA face significant bottlenecks in computational efficiency and cross-architecture transferability. Whenever a new…

Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applied to Large Language Models (LLMs). To address these issues,…

Multi-table entity matching (MEM) addresses the limitations of dual-table approaches by enabling simultaneous identification of equivalent entities across multiple data sources without unique identifiers. However, existing methods relying…

Although multimodal large language models (MLLMs) show promise in generating chart rendering code, editing charts via code presents a greater challenge. This task demands MLLMs to integrate chart understanding and reasoning capacities,…

Adjusting the outdated knowledge of large language models (LLMs) after deployment remains a major challenge. This difficulty has spurred the development of knowledge editing, which seeks to accurately and efficiently modify a model's…

Instructed code editing, where LLMs directly modify a developer's existing code based on a user instruction, is becoming a widely used interaction mode in AI coding assistants. However, few benchmarks directly evaluate this capability and…

Instruction tuning in multimodal large language models (MLLMs) generally involves cooperative learning between a backbone LLM and a feature encoder of non-text input modalities. The major challenge is how to efficiently find the synergy…

This paper introduces MMRefine, a MultiModal Refinement benchmark designed to evaluate the error refinement capabilities of Multimodal Large Language Models (MLLMs). As the emphasis shifts toward enhancing reasoning during inference,…

Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model…

Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent task conflicts, such strategy requires complex multi-stage…

Multimodal Large Language Models (MLLMs) are evaluated on various benchmarks, such as image captioning, visual question answering, and reasoning. However, many of these benchmarks include overly simple or uninformative samples, complicating…

The rise of large language models (LLMs) has created a significant disparity: industrial research labs with their computational resources, expert teams, and advanced infrastructures, can effectively fine-tune LLMs, while individual…