Related papers: Hallucination, abstention, and computable insepara…

Large language models (LLMs) have achieved remarkable performance but face critical challenges: hallucinations and high inference costs. Leveraging multiple experts offers a solution: deferring uncertain inputs to more capable experts…

Although the halting problem is undecidable, imperfect testers that fail on some instances are possible. Such instances are called hard for the tester. One variant of imperfect testers replies "I don't know" on hard instances, another…

As inductive inference and machine learning methods in computer science see continued success, researchers are aiming to describe ever more complex probabilistic models and inference algorithms. It is natural to ask whether there is a…

The consensus problem, briefly stated, consists of having processes in an asynchronous distributed system agree on a value. It is widely known that the consensus problem does not have a deterministic solution that ensures both termination…

Vision-language models (VLMs) have recently shown remarkable capabilities in visual understanding and generation, but remain vulnerable to adversarial manipulations of visual content. Prior object-hiding attacks primarily rely on…

Large-scale vision-language models have demonstrated impressive skill in handling tasks that involve both areas. Nevertheless, these models frequently experience significant issues with generating inaccurate information, which is…

The no-supervenience theorem limits the capacity of physicalist theories to provide a comprehensive account of human consciousness. The proof of the theorem is difficult to formalize because it relies on both alethic and epistemic notions…

Large language models (LLMs) produce fluent but unsupported answers - hallucinations - limiting safe deployment in high-stakes domains. We propose ECLIPSE, a framework that treats hallucination as a mismatch between a model's semantic…

Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a…

Abstractive summarization systems today produce fluent and relevant output, but often "hallucinate" statements not supported by the source text. We analyze the connection between hallucinations and training data, and find evidence that…

Reasoning with defeasible and conflicting knowledge in an argumentative form is a key research field in computational argumentation. Reasoning under various forms of uncertainty is both a key feature and a challenging barrier for automated…

Recent language models generate false but plausible-sounding text with surprising frequency. Such "hallucinations" are an obstacle to the usability of language-based AI systems and can harm people who rely upon their outputs. This work…

Large language models (LLMs) have significantly advanced natural language processing tasks, yet they are susceptible to generating inaccurate or unreliable responses, a phenomenon known as hallucination. In critical domains such as health…

Knowledge syntheses (literature reviews) are essential to health professions education (HPE), consolidating findings to advance theory and practice. However, they are labor-intensive, especially during data extraction. Artificial…

Abductive forgetting is removing variables from a logical formula while maintaining its abductive explanations. It is carried in two alternative ways depending on its intended application. Both differ from the usual forgetting, which…

Is automated hallucination detection possible? In this work, we introduce a theoretical framework to analyze the feasibility of automatically detecting hallucinations produced by large language models (LLMs). Inspired by the classical…

There are several forms of irreducibility in computing systems, ranging from undecidability to intractability to nonlinearity. This paper is an exploration of the conceptual issues that have arisen in the course of investigating speed-up…

We establish a fundamental impossibility result for a `perfect hypervisor', one that (1) preserves every observable behavior of any program exactly as on bare metal and (2) adds zero timing or resource overhead. Within this model we prove…

We consider the problem of deriving the no-signaling condition from the assumption that, as seen from a complexity theoretic perspective, the universe is not an exponential place. A fact that disallows such a derivation is the existence of…

The pursuit of high perceptual quality in image restoration has driven the development of revolutionary generative models, capable of producing results often visually indistinguishable from real data. However, as their perceptual quality…