相关论文: Check Your LLM's Secret Dictionary! Five Lines of …

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the batch level, which…

Large transformer models are known to produce high-norm tokens. In vision transformers (ViTs), such tokens have been mathematically modeled through the singular vectors of the linear approximations of layers. However, in large language…

Post-training fundamentally alters the behavior of large language models (LLMs), yet its impact on the internal parameter space remains poorly understood. In this work, we conduct a systematic singular value decomposition (SVD) analysis of…

Large language models (LLMs) take sequences of subwords as input, requiring them to effective compose subword representations into meaningful word-level representations. In this paper, we present a comprehensive set of experiments to probe…

We present an approach for assessing how multilingual large language models (LLMs) learn syntax in terms of multi-formalism syntactic structures. We aim to recover constituent and dependency structures by casting parsing as sequence…

Large Language Models (LLMs), such as GPT, are considered to learn the latent distributions within large-scale web-crawl datasets and accomplish natural language processing (NLP) tasks by predicting the next token. However, this mechanism…

Large language models (LLMs) are increasingly used in software development, but their level of software security expertise remains unclear. This work systematically evaluates the security comprehension of five leading LLMs: GPT-4o-Mini,…

Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or domain-specific senses that are often misinterpreted. While modern high-parameter Large Language Models…

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…

Multilingual LLMs demonstrate strong performance across diverse languages, yet there has been limited systematic analysis of how language information is structured within their internal representation space and how it emerges across layers.…

Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. However, how LLMs internally generate such scores remains unknown. We address…

With the significant expansion of the context window in Large Language Models (LLMs), these models are theoretically capable of processing millions of tokens in a single pass. However, research indicates a significant gap between this…

Large Language Models (LLMs) are increasingly used as evaluators of reasoning quality, yet their reliability and bias in payments-risk settings remain poorly understood. We introduce a structured multi-evaluator framework for assessing LLM…

Large language models (LLMs) contain billions of parameters, yet many exact values are not essential. We show that what matters most is the relative rank of weights-whether one connection is stronger or weaker than another-rather than…

This article describes a novel language task, the Blackbird Language Matrices (BLM) task, inspired by intelligence tests, and illustrates the BLM datasets, their construction and benchmarking, and targeted experiments on chunking and…

Generative Pretrained Transformers (GPTs) are foundational Large Language Models (LLMs) for text generation. However, individual LLMs often produce inconsistent outputs and exhibit biases, limiting their representation of diverse language…

We study how a one-layer attention-only transformer develops relevant structures while learning to sort lists of numbers. At the end of training, the model organizes its attention heads in two main modes that we refer to as…

Software developers frequently hard-code credentials such as passwords, generic secrets, private keys, and generic tokens in software repositories, even though it is strictly advised against due to the severe threat to the security of the…

With the expanding application of Large Language Models (LLMs) in various domains, it becomes imperative to comprehensively investigate their unforeseen behaviors and consequent outcomes. In this study, we introduce and systematically…