Related papers: Investigating Neurons and Heads in Transformer-bas…
Understanding the inner workings of large language models (LLMs) is crucial for advancing their theoretical foundations and real-world applications. While the attention mechanism and multi-layer perceptrons (MLPs) have been studied…
The behavior of Large Language Models (LLMs) when facing contextual information that conflicts with their internal parametric knowledge is inconsistent, with no generally accepted explanation for the expected outcome distribution. Recent…
Although large language models (LLMs) have demonstrated remarkable performance, the lack of transparency in their inference logic raises concerns about their trustworthiness. To gain a better understanding of LLMs, we conduct a detailed…
The burgeoning growth of open-sourced vision-language models (VLMs) has catalyzed a plethora of applications across diverse domains. Ensuring the transparency and interpretability of these models is critical for fostering trustworthy and…
This paper investigates the relationship between large language models' (LLMs) ability to recognize repetitive input patterns and their performance on in-context learning (ICL). In contrast to prior work that has primarily focused on…
Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. It remains a challenging problem to explain the underlying mechanisms by which LLMs…
While large language models (LLMs) have demonstrated superior multi-task capabilities, understanding the learning mechanisms behind this is still a challenging problem. In this paper, we attempt to understand such mechanisms from the…
Recent studies have suggested a processing framework for multilingual inputs in decoder-based LLMs: early layers convert inputs into English-centric and language-agnostic representations; middle layers perform reasoning within an…
Large Language Models (LLMs) excel at in-context learning, the ability to use information provided as context to improve prediction of future tokens. Induction heads have been argued to play a crucial role for in-context learning in…
Stereotypes in large language models (LLMs) can perpetuate harmful societal biases. Despite the widespread use of models, little is known about where these biases reside in the neural network. This study investigates the internal mechanisms…
Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia…
Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal,…
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…
Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear layers, the internal mechanisms by which LLMs arrive at their…
Artificial Neural Networks, the building blocks of AI, were inspired by the human brain's network of neurons. Over the years, these networks have evolved to replicate the complex capabilities of the brain, allowing them to handle tasks such…
Analogical reasoning is at the core of human cognition, serving as an important foundation for a variety of intellectual activities. While prior work has shown that LLMs can represent task patterns and surface-level concepts, it remains…
Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…
Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Large Language Models (LLMs) struggle to perform such reasoning consistently. Here we propose an approach to pinpoint and rectify…
Large language models (LLMs) have revolutionized the field of natural language processing (NLP), and recent studies have aimed to understand their underlying mechanisms. However, most of this research is conducted within a monolingual…
Language Models (LMs) have become widely used in software engineering, especially for tasks such as code generation, where they are referred to as code LMs. These models have proven effective in generating code, making it easier for…