paper-with-me

홈 › Papers

Enhancing Hallucination Detection through Noise Injection

2025-02-06 · Litian Liu, Reza Pourreza, Sunny Panchal, Apratim Bhattacharyya, Yao Qin, Roland Memisevic

Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations. Effectively detecting hallucinations is therefore crucial for the safe deployment of LLMs. Recent research has linked hallucinations to model uncertainty, suggesting that hallucinations can be detected by measuring dispersion over answer distributions obtained from a set of samples drawn from a model. While drawing from the distribution over tokens defined by the model is a natural way to obtain samples, in this work, we argue that it is sub-optimal for the purpose of detecting hallucinations. We show that detection can be improved significantly by taking into account model uncertainty in the Bayesian sense. To this end, we propose a very simple and efficient approach that perturbs an appropriate subset of model parameters, or equivalently hidden unit activations, during sampling. We demonstrate its effectiveness across a wide range of datasets and model architectures.

📄 PDF Abstract BibTeX arXiv:2502.03799

Code (0)

등록된 구현이 없습니다.

Tasks

Hallucination

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Prompt Injection Detection and Mitigation via AI Multi-Agent NLP Frameworks

2025-03-14 · Diego Gosmar, Deborah A. Dahl, Dario Gosmar

Prompt injection constitutes a significant challenge for generative AI systems by inducing unintended outputs. We introduce a multi-agent NLP framework specifically designed to address prompt injection vulnerabilities th…

Hallucination

Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models

2025-04-04 · Afshin Khadangi, Amir Sartipi, Igor Tchappi, Ramin Bahmani

Large language models (LLMs) often produce inaccurate or misleading content-hallucinations. To address this challenge, we introduce Noise-Augmented Fine-Tuning (NoiseFiT), a novel framework that leverages adaptive noise …

HallucinationLanguage ModelingLanguage Modelling

What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis

2025-02-19 · Peiran Wang, Yang Liu, Yunfei Lu, Jue Hong 외

Large language model (LLM) systems suffer from the models' unstable ability to generate valid and factual content, resulting in hallucination generation. Current hallucination detection methods heavily rely on out-of-mod…

HallucinationLanguage ModelingLanguage ModellingLarge Language Model+3

Hallucinations in Neural Automatic Speech Recognition: Identifying Errors and Hallucinatory Models

2024-01-03 · Rita Frieske, Bertram E. Shi

Hallucinations are a type of output error produced by deep neural networks. While this has been studied in natural language processing, they have not been researched previously in automatic speech recognition. Here, we d…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Hallucinationspeech-recognition+1

CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models

2026-04-13 · Linggang Kong, Lei Wu, Yunlong Zhang, Xiaofeng Zhong 외 arxiv

Despite the groundbreaking advancements made by large language models (LLMs), hallucination remains a critical bottleneck for their deployment in high-stakes domains. Existing classification-based methods mainly rely on …