← Back to all news
arXiv AI By Urja Pawar, Rajitha Ramanayake, Owen O'Neill, Nabeel Kemal, Abhishek Mandal, Houssem Chatbri, Christopher Martin

From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jun 9

BEACON: Behavioral Entropy Aggregation for Cross-Model Hallucination Detection in Large Language Models

arXiv:2606. 07528v1 Announce Type: cross Abstract: Hallucination in large language models (LLMs), defined as the generation of factually incorrect or unsupported content, remains a critical barrier to reliable deployment.

By Naveen Bera, Pulijala Sai Nikhila, Kondaguduru Abhiram, Shaik Gayaz Ali, Shoaib Sadiq Salehmohamed, Shaik Mohammed Omar, Jinal Prashant Thakkar, Hansika Aredla, Shalmali Ayachit
llmsragbenchmarkssafety
More like this →
arXiv Machine Learning
Aug 27

Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification

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.

By Dylan Bouchard, Mohit Singh Chauhan, Zeya Ahmad, Ho-Kyeong Ra
llmsbenchmarkssafety
More like this →
arXiv AI
Oct 2

Signed Lexical Confidence for Risk-Calibrated Intent Routing

The paper introduces a signed lexical gate that combines a sentence classifier’s logit margin with a sparse lexical model’s support for the predicted intent, assigning positive evidence to lexical agreement and negative evidence to a lexically favored competing intent. This gate retains more information than unsigned lexical confidence or a hard agreement rule and is calibrated via an independent binomial procedure to meet specified risk targets. Experiments on BANKING77, CLINC150, and HWU64 show that the proposed score reduces the area under the risk‑coverage curve by up to 15.8% and increases accepted coverage at low error rates, offering a compact, interpretable confidence enhancement for risk‑calibrated intent routing.

By Yezhou Cheng, Zehua Yang, Bojun Lin
More like this →
arXiv AI
Sep 17

Label-Confidence-Aware Uncertainty Estimation in Natural Language Generation

The paper introduces Label-Confidence-Aware Uncertainty Quantification (LCA-UQ), a method that uses Pointwise Kullback-Leibler divergence to align global entropy from multiple stochastic samples with the local confidence of a candidate answer. By bridging this gap, LCA-UQ improves the reliability and stability of uncertainty assessments in natural language generation. Experiments on popular LLMs and NLP datasets show that label sources significantly influence classification and that LCA-UQ outperforms existing uncertainty estimation approaches.

By Qinhong Lin, Yinglun Feng, Yuhao Zhang, Zhongliang Yang, Linna Zhou
llmsnlpsafety
More like this →