The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2603. 24929v2 Announce Type: replace Abstract: Understanding and quantifying uncertainty in large language model (LLM) outputs is critical for reliable deployment.
arXiv:2606. 09875v1 Announce Type: cross Abstract: Large language models hallucinate confidently, making uncertainty quantification (UQ) essential for reliable deployment.
The paper introduces Functional Entropy, a new uncertainty quantification technique for assessing the functional correctness of code generated by large language models. It evaluates token‑probability and sampling‑based methods across three programming languages and five LLMs, finding that token‑probability approaches generalize well while NLI‑based sampling fails due to semantic clustering. Functional equivalence methods, which replace NLI with an LLM‑based functional assessment, achieve superior AUROC and calibration in most model‑benchmark combinations.
The paper investigates hallucination detection in black‑box large language models by leveraging two accessible signals: semantic entropy, which captures disagreement among sampled response meanings, and token‑level uncertainty derived from log‑probabilities. It introduces a TopK aggregation technique, a hybrid CoCoA method combining uncertainty with semantic dissimilarity, and two supervised approaches—Gated and Stacked—that integrate token and semantic features. Across seven benchmarks and four language models, the supervised Stacked method performs best in many cases, while TopK and CoCoA remain competitive without labeled data, though all methods require careful threshold calibration.
arXiv:2511. 16275v4 Announce Type: replace-cross Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language models (LLMs) in safety-critical scenarios, as it enables them to abstain from responding when uncertain, thereby avoiding hallucinations, i.
Uncertainty estimation is essential not only for the trustworthy deployment of large language models (LLMs) but also as a foundation for self-refinement in LLM generation. However, existing approaches operate at suboptimal granularities: token-level scores lack semantic coherence, while sequence-level scores fail to localize errors.