Related papers: Hidden Measurement Error in LLM Pipelines Distorts…
The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments (TEEs) offer a promising solution, their performance limits can lead to a…
As Large Language Models (LLMs) advance toward embodied AI agents operating in physical environments, a fundamental question emerges: can models trained on text corpora reliably reason about complex physics while adhering to safety…
Leakage errors are unwanted transfer of population outside of a defined computational subspace and they occur in almost every platform for quantum computing. While prevalent, leakage is often overlooked when measuring and reporting the…
Large Language Models (LLMs) are increasingly used to automate software generation in embedded machine learning workflows, yet their outputs often fail silently or behave unpredictably. This article presents an empirical investigation of…
Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…
Large language models (LLMs) are increasingly prevalent in security research. Their unique characteristics, however, introduce challenges that undermine established paradigms of reproducibility, rigor, and evaluation. Prior work has…
Most enterprise document AI today is a pipeline. Parse, index, retrieve, generate. Each of those stages has been studied to death on its own -- what's still hard is evaluating the system as a whole. We built EnterpriseDocBench to take a…
While large language models (LLMs) excel at many domain-specific tasks, their ability to deeply comprehend and reason about full-length academic papers remains underexplored. Existing benchmarks often fall short of capturing such depth,…
Large language models (LLMs) are increasingly trained to abstain on difficult questions by answering unknown. However, we observe that LLMs often misuse this option: they output unknown even when LLMs can actually solve the questions, or…
Edge applications increasingly demand custom hardware, yet Field-Programmable Gate Array (FPGA) design requires expertise that domain engineers lack. Large Language Models (LLMs) promise to bridge this gap through zero-knowledge hardware…
While prior work has focused on projecting adversarial examples back onto the manifold of natural data to restore safety, we argue that a comprehensive understanding of AI safety requires characterizing the unsafe regions themselves. This…
With the rapid adoption of LLM-based chatbots, there is a pressing need to evaluate what humans and LLMs can achieve together. However, standard benchmarks, such as MMLU, measure LLM capabilities in isolation (i.e., "AI-alone"). Here, we…
How much do large language models actually hallucinate when answering questions grounded in provided documents? Despite the critical importance of this question for enterprise AI deployments, reliable measurement has been hampered by…
This paper surveys evaluation techniques to enhance the trustworthiness and understanding of Large Language Models (LLMs). As reliance on LLMs grows, ensuring their reliability, fairness, and transparency is crucial. We explore algorithmic…
Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…
LLM-judged benchmarks are increasingly used to evaluate complex model behaviors, yet their design introduces failure modes absent in conventional ground-truth based benchmarks. We argue that without tight objectives and verifiable…
Large Language Models (LLMs) are now integral across various domains and have demonstrated impressive performance. Progress, however, rests on the premise that benchmark scores are both accurate and reproducible. We demonstrate that the…
Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabilities. Evaluating open-source LLMs through leaderboards faces persistent issues like data…
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 model (LLM) evaluation is increasingly costly, prompting interest in methods that speed up evaluation by shrinking benchmark datasets. Benchmark prediction (also called efficient LLM evaluation) aims to select a small subset…