Related papers: DeepEdit: Knowledge Editing as Decoding with Const…
Knowledge editing methods (KEs) can update language models' obsolete or inaccurate knowledge learned from pre-training. However, KEs can be used for malicious applications, e.g., inserting misinformation and toxic content. Knowing whether a…
Large language models (LLMs) demonstrate remarkable text comprehension and generation capabilities but often lack the ability to utilize up-to-date or domain-specific knowledge not included in their training data. To address this gap, we…
A common solution for mitigating outdated or incorrect information in Large Language Models (LLMs) is to provide updated facts in-context or through knowledge editing. However, these methods introduce knowledge conflicts when the knowledge…
Lifelong knowledge editing enables continuous, precise updates to outdated knowledge in large language models (LLMs) without computationally expensive full retraining. However, existing methods often accumulate errors throughout the editing…
Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging…
Recent knowledge editing methods have primarily focused on modifying structured knowledge in large language models. However, this task setting overlooks the fact that a significant portion of real-world knowledge is stored in an…
Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they sometimes provide incorrect responses. To address this issue, knowledge editing techniques have emerged as effective methods for…
Large Language Models (LLMs) often retain inaccurate or outdated information from pre-training, leading to incorrect predictions or biased outputs during inference. While existing model editing methods can address this challenge, they…
Recent advances in image editing models have shown remarkable progress. A common architectural design couples a multimodal large language model (MLLM) encoder with a diffusion decoder, as seen in systems such as Step1X-Edit and…
Large Language Models (LLMs), despite their remarkable capabilities, rely on singular, pre-dominant reasoning paradigms, hindering their performance on intricate problems that demand diverse cognitive strategies. To address this, we…
Large Language Models (LLMs) have demonstrated remarkable efficiency in tackling various tasks based on human instructions, but studies reveal that they often struggle with tasks requiring reasoning, such as math or physics. This limitation…
When performing reasoning tasks with user-specific requirements, such as strict output formats, large language models (LLMs) often prioritize reasoning over adherence to detailed instructions. Fine-tuning LLMs on supervised datasets to…
Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted parameter modifications, with meta-learning-based model editing…
Constrained decoding approaches aim to control the meaning or style of text generated by the pre-trained large language models (LLMs or also PLMs) for various tasks at inference time. However, these methods often guide plausible…
Knowledge editing (KE) provides a lightweight alternative to repeated fine-tuning of LLMs. However, most existing KE methods target dense feed-forward layers, while modern LLMs increasingly adopt Mixture-of-Experts (MoE) architectures for…
As Large Language Models (LLMs) scale up and gain powerful Chain-of-Thoughts (CoTs) reasoning abilities, practical resource constraints drive efforts to distill these capabilities into more compact Smaller Language Models (SLMs). We find…
Despite the advances in large language models (LLMs), how they use their knowledge for reasoning is not yet well understood. In this study, we propose a method that deconstructs complex real-world questions into a graph, representing each…
Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability. While model editing methods have been developed to address such errors without full re-training, they…
Multimodal knowledge editing represents a critical advancement in enhancing the capabilities of Multimodal Large Language Models (MLLMs). Despite its potential, current benchmarks predominantly focus on coarse-grained knowledge, leaving the…
Novel research ideas play a critical role in advancing scientific inquiries. Recent advancements in Large Language Models (LLMs) have demonstrated their potential to generate novel research ideas by leveraging large-scale scientific…