Related papers: Beyond the Mean: Within-Model Reliable Change Dete…
Large language models (LLMs) acquire substantial world knowledge during pre-training, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). However, the impact of SFT on a model's knowledge remains…
Large Language Models (LLMs) have shown strong capabilities in document re-ranking, a key component in modern Information Retrieval (IR) systems. However, existing LLM-based approaches face notable limitations, including ranking…
Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation. We define evaluation-context…
Hypernetwork-based methods such as Doc-to-LoRA internalize a document into an LLM's weights in a single forward pass, but they fail systematically on conflicts: when the document contradicts pretraining knowledge, accuracy collapses to…
Large language models (LLMs) excel at numerical estimation but struggle to correctly quantify uncertainty. We study how well LLMs construct confidence intervals around their own answers and find that they are systematically overconfident.…
Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them…
As large language models (LLMs) often generate plausible but incorrect content, error detection has become increasingly critical to ensure truthfulness. However, existing detection methods often overlook a critical problem we term as…
Information retrieval (IR) evaluation remains challenging due to incomplete IR benchmark datasets that contain unlabeled relevant chunks. While LLMs and LLM-human hybrid strategies reduce costly human effort, they remain prone to LLM…
Large language models (LLMs) often generate content with unsupported or unverifiable content, known as "hallucinations." To address this, retrieval-augmented LLMs are employed to include citations in their content, grounding the content in…
The validity screen (Cacioli, 2026d, 2026e) classifies LLM confidence signals as Valid, Indeterminate, or Invalid. We test whether these classifications predict selective prediction performance. Twenty frontier LLMs from seven families were…
We report that model quantisation restructures domain-level metacognitive efficiency in LLMs rather than degrading it uniformly. Evaluating Llama-3-8B-Instruct on the same 3,000 questions at Q5_K_M and f16 precision, we find that M-ratio…
The problem of quickest change detection in a sequence of independent observations is considered. The pre-change distribution is assumed to be known, while the post-change distribution is unknown. Two tests based on post-change density…
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…
The rise of large language models (LLMs) has significantly influenced the quality of information in decision-making systems, leading to the prevalence of AI-generated content and challenges in detecting misinformation and managing…
Large Language Models (LLMs) often struggle to use information across long inputs effectively. Prior work has identified positional biases, such as the Lost in the Middle (LiM) effect, where models perform better when information appears at…
Modern LLMs struggle with efficient updates, as each new pretrained model version requires repeating expensive alignment processes. This challenge also applies to domain- or languagespecific models, where fine-tuning on specialized data…
We audit alignment-induced shifts in residual-stream activations of three open-weight instruction-tuned LLMs (Llama-3.1-8B-Instruct, Gemma-2-9B-it, Qwen-2.5-7B-Instruct) using the effective rank of the alignment modification matrix on…
Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…
Common Large Language model (LLM) evaluations rely on demonstration examples to steer models' responses to the desired style. While the number of examples used has been studied and standardized, the choice of how to format examples is less…
Problem. "Thinking" LLMs (TLLMs) expose explicit or hidden reasoning traces and are widely believed to generalize better on complex tasks than direct LLMs. Whether this promise carries to noisy, heavy-tailed and regime-switching financial…