This work proposes a method to rank feed-forward neurons at the final prompt token using a custom neuron selection dataset, and transfers the selected neuron identities to train hallucination classifiers on other factual question answering datasets.
Abstract
Hallucination in large language models reduces their reliability and slows adoption. Various white-box studies have used internal representations to detect patterns of truthfulness and factuality. A less-studied approach is to identify feed-forward neurons correlated with hallucination. We propose a method to rank feed-forward neurons at the final prompt token using a custom neuron selection dataset. We transfer the selected neuron identities to train hallucination classifiers on other factual question answering datasets. Our work provides empirical evidence that probes trained using the features from the selected neurons perform on par with probes trained on internal states. We also analyze the distribution of selected neurons and the effect of layer depth on detection performance.
Interpretable machine learning for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claimed to detect and causally influence behaviors such as factuality recall, safety alignment, and hallucination. These claims have important implications for model auditing...
Huseyin Cavus, Sebin Sabu, J. Spear et al.· 0 citations
InnerExpert is introduced, the first method to leverage MoE-specific signals for per-token hallucination detection, and shows that InnerExpert outperforms existing methods across five datasets and two MoE architectures.
João Fonseca, Rodrigo Rodrigues, Paolo Romano· 0 citations
Large Language Models (LLMs) frequently exhibit hallucinations, presenting a major barrier to reliability in complex reasoning tasks. While traditional detection methods rely on output-based confidence metrics, these logits are often miscalibrated by modern alignment techniques. In this paper, we investigate the tempor...
This work introduces a two-stage keyword-perturbation method for hallucination detection and extends the same probabilistic framework to four hallucination regimes: knowledge deficit, wrong knowledge, context distraction, and unstable inference.
Xu-Han Tong, Hao-Yue Bai, Da-Wei Zhou et al.· 0 citations
Large language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout uncertainty quantification, and temperature-scaled calibration for response-level ha...
Large language models are increasingly used for financial question answering, while they are prone to generating hallucinated content. In this research, we propose a multi-signal framework for hallucination detection and mitigation. Our framework combines six signals (entailment, semantic similarity, claim verification...
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
