Related papers: Detection Without Correction: A Robust Asymmetry i…
Recently developed large language models have achieved remarkable success in generating fluent and coherent text. However, these models often tend to 'hallucinate' which critically hampers their reliability. In this work, we address this…
Detecting hallucinations in large language model (LLM) outputs is pivotal, yet traditional fine-tuning for this classification task is impeded by the expensive and quickly outdated annotation process, especially across numerous vertical…
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…
Detecting hallucinations in Large Language Model-generated text is crucial for their safe deployment. While probing classifiers show promise, they operate on isolated layer-token pairs and are LLM-specific, limiting their effectiveness and…
Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, this improved reasoning ability often comes with…
Large language models (LLMs) are known to "hallucinate" by generating false or misleading outputs. Hallucinations pose various harms, from erosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses…
Hallucination detection remains a fundamental challenge for the safe and reliable deployment of large language models (LLMs), especially in applications requiring factual accuracy. Existing hallucination benchmarks often operate at the…
In explainable AI, Concept Activation Vectors (CAVs) are typically obtained by training linear classifier probes to detect human-understandable concepts as directions in the activation space of deep neural networks. It is widely assumed…
LLMs often produce fluent but incorrect answers, yet detecting such hallucinations typically requires multiple sampling passes or post-hoc verification, adding significant latency and cost. We hypothesize that intermediate layers encode…
Large language models are extensively applied across a wide range of tasks, such as customer support, content creation, educational tutoring, and providing financial guidance. However, a well-known drawback is their predisposition to…
Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but…
Hallucinations in Large Language Models (LLMs) pose a significant challenge, generating misleading or unverifiable content that undermines trust and reliability. Existing evaluation methods, such as KnowHalu, employ multi-stage verification…
Generative models are prone to hallucinations: plausible but incorrect structures absent in the ground truth. This issue is problematic in image restoration for safety-critical domains such as medical imaging, industrial inspection, and…
Graph-based Retrieval-Augmented Generation (GraphRAG) enhances Large Language Models (LLMs) by incorporating external knowledge from linearized subgraphs retrieved from knowledge graphs. However, LLMs struggle to interpret the relational…
Large language models (LLMs) can be prone to hallucinations - generating unreliable outputs that are unfaithful to their inputs, external facts or internally inconsistent. In this work, we address several challenges for post-hoc…
Large language models hallucinate during multi-step reasoning, but most existing detectors operate at the trace level: they assign one confidence score to a full output, fail to localize the first error, and often require multiple sampled…
Hallucinations in large language models (LLMs) - instances where models generate plausible but factually incorrect information - present a significant challenge for AI. We introduce "Ask a Local", a novel hallucination detection method…
Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated…
AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned. We thus…
To mitigate hallucinations in large language models (LLMs), we propose a framework that focuses on errors induced by prompts. Our method extends a chain-style knowledge distillation approach by incorporating a programmable module that…