16 papers
MIRAGE: Defending Long-Form RAG Against Misinformation Pollution
Saadeldine Eletter, Ruihong Zeng, Yuxia Wang +3
Retrieval-Augmented Generation (RAG) improves factuality by grounding LLMs in external evidence, but real-world retrieval is often polluted: semantically relevant passages may cont…
Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads
Artem Vazhentsev, Lyudmila Rvanova, Gleb Kuzmin +8
While large language models (LLMs) have become highly capable, they remain prone to factual inaccuracies, commonly referred to as "hallucinations." Uncertainty quantification (UQ)…
IDLM: Inverse-distilled Diffusion Language Models
David Li, Nikita Gushchin, Dmitry Abulkhanov +4
Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To ad…
Why Don't You Know? Evaluating the Impact of Uncertainty Sources on Uncertainty Quantification in LLMs
Maiya Goloburda, Roman Vashurin, Fedor Chernogorskii +4
As Large Language Models (LLMs) are increasingly deployed in real-world applications, reliable uncertainty quantification (UQ) becomes critical for safe and effective use. Most exi…
Uncertainty Quantification for Large Language Diffusion Models
Artem Vazhentsev, Vladislav Smirnov, David Li +3
Large Language Diffusion Models (LLDMs) are emerging as an alternative to autoregressive models, offering faster inference through higher parallelism. Similar to autoregressive LLM…
Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search
Ekaterina Fadeeva, Maiya Goloburda, Aleksandr Rubashevskii +5
Consistency-based methods have emerged as an effective approach to uncertainty quantification (UQ) in large language models. These methods typically rely on several generations obt…