Related papers: Talking Heads: Understanding Inter-layer Communica…
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…
Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…
Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…
Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to over-reliance on memorized training examples. However, the…
The transformer structure employed in large language models (LLMs), as a specialized category of deep neural networks (DNNs) featuring attention mechanisms, stands out for their ability to identify and highlight the most relevant aspects of…
A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate to its function. We take a high-level geometric approach to…
Self-supervised large language models have demonstrated the ability to perform Machine Translation (MT) via in-context learning, but little is known about where the model performs the task with respect to prompt instructions and…
Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers…
Language Models (LMs) have shown their application for tasks pertinent to code and several code~LMs have been proposed recently. The majority of the studies in this direction only focus on the improvements in performance of the LMs on…
Pretrained language models (LMs) encode implicit representations of knowledge in their parameters. However, localizing these representations and disentangling them from each other remains an open problem. In this work, we investigate…
Transformer networks, particularly those achieving performance comparable to GPT models, are well known for their robust feature extraction abilities. However, the nature of these extracted features and their alignment with human-engineered…
Large Language Models (LLMs), powered by Transformers, have demonstrated human-like intelligence capabilities, yet their underlying mechanisms remain poorly understood. This paper presents a novel framework for interpreting LLMs as…
Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…
Large language models (LLMs) are powerful models that can learn concepts at the inference stage via in-context learning (ICL). While theoretical studies, e.g., \cite{zhang2023trained}, attempt to explain the mechanism of ICL, they assume…
Categorization is a core component of human linguistic competence. We investigate how a transformer-based language model (LM) learns linguistic categories by comparing its behaviour over the course of training to behaviours which…
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…
Interactive speech recognition systems must generate words quickly while also producing accurate results. Two-pass models excel at these requirements by employing a first-pass decoder that quickly emits words, and a second-pass decoder that…
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…
Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…
Mechanistic interpretability research seeks to reveal the inner workings of large language models, yet most work focuses on classification or generative tasks rather than summarization. This paper presents an interpretability framework for…