相关论文: SAKE: Steering Activations for Knowledge Editing

Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effective, existing methods often apply a fixed steering strength to…

The factual knowledge acquired during pre-training and stored in the parameters of Language Models (LMs) can be useful in downstream tasks (e.g., question answering or textual inference). However, some facts can be incorrectly induced or…

Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modify LLM knowledge instead of removing it. Though editing and…

Current self-correction approaches in text-to-SQL face two critical limitations: 1) Conventional self-correction methods rely on recursive self-calls of LLMs, resulting in multiplicative computational overhead, and 2) LLMs struggle to…

Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks, commonsense reasoning is one of them. Researchers typically address these issues by retrieving related knowledge from knowledge graphs or…

Advances in NLP have yielded impressive results for the task of machine reading comprehension (MRC), with approaches having been reported to achieve performance comparable to that of humans. In this paper, we investigate whether…

Multimodal large language models (MLLMs) are prone to non-factual or outdated knowledge issues, which can manifest as misreading and misrecognition errors due to the complexity of multimodal knowledge. Previous benchmarks have not…

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

Knowledge Editing is a technique that updates large language models (LLMs) with new information to maintain their world knowledge. This approach avoids the need to rebuild the model from scratch, thereby addressing the high costs associated…

Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation of specific knowledge memories and the behavior of language…

Previous studies have shown that large language models (LLMs) like GPTs store massive factual knowledge in their parameters. However, the stored knowledge could be false or out-dated. Traditional knowledge editing methods refine LLMs via…

Locate-then-Edit Knowledge Editing (LEKE) is a key technique for updating large language models (LLMs) without full retraining. However, existing methods assume a single-user setting and become inefficient in real-world multi-client…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

The significant progress of large language models (LLMs) provides a promising opportunity to build human-like systems for various practical applications. However, when applied to specific task domains, an LLM pre-trained on a…

Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…

Enabling artificial intelligence systems, particularly large language models, to integrate new knowledge and flexibly apply it during reasoning remains a central challenge. Existing knowledge editing approaches emphasize atomic facts,…

Large Language Models (LLMs) require continuous updates to maintain accurate and current knowledge as the world evolves. While existing knowledge editing approaches offer various solutions for knowledge updating, they often struggle with…

Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations…

Knowledge representation and reasoning systems represent knowledge as collections of facts and rules. KRRs can represent complex concepts and relations, and they can query and manipulate information in sophisticated ways. Unfortunately, the…

Attention steering is an important technique for controlling model focus, enabling capabilities such as prompt highlighting, where the model prioritises user-specified text. However, existing attention steering methods require explicit…