Related papers: Does Editing Provide Evidence for Localization?

Systematic reviews are crucial for synthesizing scientific evidence but remain labor-intensive, especially when extracting detailed methodological information. Large language models (LLMs) offer potential for automating methodological…

Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual effort and expertise required. While Large Language Models…

Model interpretability and model editing are crucial goals in the age of large language models. Interestingly, there exists a link between these two goals: if a method is able to systematically edit model behavior with regard to a human…

Hypothesis formulation and testing are central to empirical research. A strong hypothesis is a best guess based on existing evidence and informed by a comprehensive view of relevant literature. However, with exponential increase in the…

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to individual preferences while maintaining alignment with…

Measuring innovation often relies on context-specific proxies and on expert evaluation. Hence, empirical innovation research is often limited to settings where such data is available. We investigate how large language models (LLMs) can be…

Large Language Models (LLMs) have demonstrated remarkable abilities in text comprehension and logical reasoning, indicating that the text representations learned by LLMs can facilitate their language processing capabilities. In…

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Designing proper experiments and selecting optimal intervention targets is a longstanding problem in scientific or causal discovery. Identifying the underlying causal structure from observational data alone is inherently difficult.…

LLM-based Automatic Prompt Optimization, which typically utilizes LLMs as Prompt Optimizers to self-reflect and refine prompts, has shown promising performance in recent studies. Despite the success, the underlying mechanism of this…

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Large Language Models (LLMs) have revolutionised the capability of AI models in comprehending and generating natural language text. They are increasingly being used to empower and deploy agents in real-world scenarios, which make decisions…

Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an essential capability for adaptive reasoning and efficient…

Evaluations of model editing currently only use the `next few token' completions after a prompt. As a result, the impact of these methods on longer natural language generation is largely unknown. We introduce long-form evaluation of model…

While self-correction has shown promise in improving LLM outputs in terms of style and quality (e.g. Chen et al., 2023b; Madaan et al., 2023), recent attempts to self-correct logical or reasoning errors often cause correct answers to become…

Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserving its behavior on all other inputs. This process typically involves two stages: identifying the…

Text-guided diffusion models have significantly advanced image editing, enabling highly realistic and local modifications based on textual prompts. While these developments expand creative possibilities, their malicious use poses…

This pilot study explores the localisation capabilities of state-of-the-art multilingual AI models when translating figurative language, such as idioms and puns, from English into a diverse range of global languages. It expands on existing…

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,…

As the modern tool of choice for question answering, large language models (LLMs) are expected to deliver answers with up-to-date knowledge. To achieve such ideal question-answering systems, locating and then editing outdated knowledge in…