相关论文: Natural Fingerprints of Large Language Models

Prominent works in the field of Natural Language Processing have long attempted to create new innovative models by improving upon previous model training approaches, altering model architecture, and developing more in-depth datasets to…

Large Language Models (LLMs) are being adopted across a wide range of tasks, including decision-making processes in industries where bias in AI systems is a significant concern. Recent research indicates that LLMs can harbor implicit biases…

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Large language models (LMs) have rapidly become a mainstay in Natural Language Processing. These models are known to acquire rich linguistic knowledge from training on large amounts of text. In this paper, we investigate if pre-training on…

We study subliminal learning, a surprising phenomenon where language models transmit behavioral traits via semantically unrelated data. In our main experiments, a "teacher" model with some trait T (such as liking owls or being misaligned)…

Understanding training dynamics and feature evolution is crucial for the mechanistic interpretability of large language models (LLMs). Although sparse autoencoders (SAEs) have been used to identify features within LLMs, a clear picture of…

Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present…

The remarkable success of Large Language Models (LLMs) in generative tasks has raised fundamental questions about the nature of their acquired capabilities, which often appear to emerge unexpectedly without explicit training. This paper…

Does GPT know you? The answer depends on your level of public recognition; however, if your information was available on a website, the answer could be yes. Most Large Language Models (LLMs) memorize training data to some extent. Thus, even…

Language models (LMs) can exhibit human-like behaviour, but it is unclear how to describe this behaviour without undue anthropomorphism. We formalise a behaviourist view of LM character traits: qualities such as truthfulness, sycophancy, or…

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications.…

Competency modeling is widely used in human resource management to select, develop, and evaluate talent. However, traditional expert-driven approaches rely heavily on manual analysis of large volumes of interview transcripts, making them…

The rapid advancements in large language models (LLMs) have significantly improved their ability to generate natural language, making texts generated by LLMs increasingly indistinguishable from human-written texts. While recent research has…

Large Language Models (LLMs) display notable variation in multilingual behavior, yet the role of genealogical language structure in shaping this variation remains underexplored. In this paper, we investigate whether LLMs exhibit sensitivity…

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update…

Large language models (LLM) have revolutionized the processing of natural language. Although first benchmarks of the process modeling abilities of LLM are promising, it is currently under debate to what extent an LLM can generate good…

Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language. To what extent can LLMs generalize across these…

Large language models (LLMs) are increasingly used as decision-support tools in data-constrained scientific workflows, where correctness and validity are critical. However, evaluation practices often emphasize stability or reproducibility…

The capability of large language models (LLMs) to generate, debug, and explain code has sparked the interest of researchers and educators in undergraduate programming, with many anticipating their transformative potential in programming…

Phase transitions have been proposed as the origin of emergent abilities in large language models (LLMs), where new capabilities appear abruptly once models surpass critical thresholds of scale. Prior work, such as that of Wei et al.,…