Related papers: Are LLM Uncertainty and Correctness Encoded by the…
We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as constraint satisfaction problems and use this framework to…
Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavior steering. Yet, a fundamental question remains unanswered:…
LLMs show strong performance in code generation, but their outputs lack correctness guarantees. Sample-based uncertainty estimators address this by generating multiple candidate programs and measuring their disagreement. However, existing…
Recent developments in Large Language Model (LLM) capabilities have brought great potential but also posed new risks. For example, LLMs with knowledge of bioweapons, advanced chemistry, or cyberattacks could cause violence if placed in the…
Large language models (LLMs) have delivered significant breakthroughs across diverse domains but can still produce unreliable or misleading outputs, posing critical challenges for real-world applications. While many recent studies focus on…
Large Language Models (LLMs) can correct their self-generated responses, but a decline in accuracy after self-correction is also witnessed. To have a deeper understanding of self-correction, we endeavor to decompose, evaluate, and analyze…
Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In…
Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs.…
Large language models (LLMs) enable powerful zero-shot recommendations by leveraging broad contextual knowledge, yet predictive uncertainty and embedded biases threaten reliability and fairness. This paper studies how uncertainty and…
Multilingual large language models (LLMs) exhibit strong cross-linguistic generalization, yet medium to low resource languages underperform on common benchmarks such as ARC-Challenge, MMLU, and HellaSwag. We analyze activation patterns in…
Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks. Despite recent advances, these models are still prone to what are commonly known as hallucinations, causing them to emit…
There is a growing literature on reasoning by large language models (LLMs), but the discussion on the uncertainty in their responses is still lacking. Our aim is to assess the extent of confidence that LLMs have in their answers and how it…
Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction. Subsequent stages of post-training often introduce new facts outwith the parametric knowledge, giving rise to…
Fine-tuning large language models can improve task specific performance, although a general understanding of what the fine-tuned model has learned, forgotten and how to trust its predictions is still missing. We derive principled…
The generation of texts using Large Language Models (LLMs) is inherently uncertain, with sources of uncertainty being not only the generation of texts, but also the prompt used and the downstream interpretation. Within this work, we provide…
The finetuning of Large Language Models (LLMs) has significantly advanced their instruction-following capabilities, yet the underlying computational mechanisms driving these improvements remain poorly understood. This study systematically…
Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…
Empowering large language models to accurately express confidence in their answers is essential for trustworthy decision-making. Previous confidence elicitation methods, which primarily rely on white-box access to internal model information…
In recent years, there has been a growing use of generative AI, and large language models (LLMs) in particular, to support both the assessment and generation of scientific work. Although some studies have shown that LLMs can, to a certain…
Large Language Models (LLMs) have gained significant popularity in recent years for their ability to answer questions in various fields. However, these models have a tendency to "hallucinate" their responses, making it challenging to…