相关论文: Adaptive Circuit Behavior and Generalization in Me…

Underlying mechanisms of memorization in LLMs -- the verbatim reproduction of training data -- remain poorly understood. What exact part of the network decides to retrieve a token that we would consider as start of memorization sequence?…

Different fields in applied machine learning such as computer vision, speech or natural language processing have been building domain-specialised solutions. Currently, we are witnessing an opposing trend towards developing more generalist…

Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and robustly -- the hallmarks of artificial general intelligence…

We study whether automatically-induced prompts that effectively extract information from a language model can also be used, out-of-the-box, to probe other language models for the same information. After confirming that discrete prompts…

Robots are increasingly common in industry and daily life, such as in nursing homes where they can assist staff. A key challenge is developing intuitive interfaces for easy communication. The use of Large Language Models (LLMs) like GPT-4…

While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and safe deployment. Existing surveys in explainable AI largely focus on post-hoc explanation…

Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known as jailbreaks. Unlike traditional adversarial examples…

Humans acquire language through implicit learning, absorbing complex patterns without explicit awareness. While LLMs demonstrate impressive linguistic capabilities, it remains unclear whether they exhibit human-like pattern recognition…

One goal of AI (and AGI) is to identify and understand specific mechanisms and representations sufficient for general intelligence. Often, this work manifests in research focused on architectures and many cognitive architectures have been…

Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions. Recent meta-learning methods have made significant progress in…

Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque. This lack of transparency presents challenges such as…

Large language models (LLMs) demonstrate great potential for problems with implicit graphical structures, while recent works seek to enhance the graph reasoning capabilities of LLMs through specialized instruction tuning. The resulting…

Prompt tuning for vision-language models such as CLIP involves optimizing the text prompts used to generate image-text pairs for specific downstream tasks. While hand-crafted or template-based prompts are generally applicable to a wider…

Why can pre-trained language models (PLMs) learn universal representations and effectively adapt to broad NLP tasks differing a lot superficially? In this work, we empirically find evidence indicating that the adaptations of PLMs to various…

This paper tests whether large language models (LLMs) can support interpretative citation context analysis (CCA) by scaling in thick, text-grounded readings of a single hard case rather than scaling up typological labels. It foregrounds…

In the field of eXplainable AI (XAI) in language models, the progression from local explanations of individual decisions to global explanations with high-level concepts has laid the groundwork for mechanistic interpretability, which aims to…

Transformer-based language models exhibit In-Context Learning (ICL), where predictions are made adaptively based on context. While prior work links induction heads to ICL through a sudden jump in accuracy, this can only account for ICL when…

Generalization across domains requires stable structure that links the source and target distributions. Building on causal transportability theory, we study a sequential prediction setting in which the target predictor can be represented as…

The need for explainable AI (XAI) is well established but relatively little has been published outside of the supervised learning paradigm. This paper focuses on a principled approach to applying explainability and interpretability to the…

Rote learning is a memorization technique based on repetition. Many researchers argue that rote learning hinders generalization because it encourages verbatim memorization rather than deeper understanding. This concern extends even to…