An official website of the United States government
Hallucinations in large language models (LLMs), where they generate fluent but factually incorrect outputs, pose challenges for applications requiring strict truthfulness. This work proposes a multi-faceted approach to detect such hallucinations across various language tasks. We leverage automatic data annotation using a proprietary LLM, fine-tuning of the Mistral-7B-instruct-v0.2 model on annotated and benchmark data, role-based and rationale-based prompting strategies, and an ensemble method combining different model outputs through majority voting. This comprehensive framework aims to improve the robustness and reliability of hallucination detection for LLM generations. Code and data1 1 Introduction The modern natural language generation (NLG) (OpenAI et al., 2023; Touvron et al., 2023) landscape faces two interconnected challenges: firstly, current neural models have a tendency to produce f luent yet inaccurate outputs, and secondly, our evaluation metrics are better suited for assessing f luency rather than correctness(Bang et al., 2023; Guerreiro et al., 2023). This phenomenon, known as "hallucination," (Ji et al., 2023) where neural networks generate plausible-sounding but factually incorrect outputs, is a significant hurdle, especially for NLG applications that require strict adherence to correctness. For instance, in machine translation(Lee et al., 2019), producing a fluent translation that deviates from the source text’s meaning renders the entire translation pipeline unreliable. This issue may arise as LLMs are trained on vast amounts of data from the internet, which can contain inaccuracies, biases, and false information. Also, it may arise due improper representations learned during training even if good quality data is 1https://github.com/souvikdgp16/shroom_compos_mentis used. As a result, LLMs can sometimes hallucinate or fabricate details, especially when prompted to discuss topics outside their training data or make inferences beyond their capabilities. Hallucination detection (Liu et al., 2022), also known as factual verification or truthfulness evaluation, identifies and mitigates these hallucinations in the outputs of LLMs. This is an active area of research and development, as it is crucial for ensuring the reliability and trustworthiness of LLMgenerated content, particularly in high-stakes domains such as healthcare, finance, and legal applications. In this task, the primary focus will be to classify whether a generation is hallucinated. This work proposes a multi-faceted approach to detecting hallucinations in large language models.
more »
« less
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection
Neural sequence generation models are known to “hallucinate”, by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate their impact. In this work, we first identify internal model symptoms of hallucinations by analyzing the relative token contributions to the generation in contrastive hallucinated vs. non-hallucinated outputs generated via source perturbations. We then show that these symptoms are reliable indicators of natural hallucinations, by using them to design a lightweight hallucination detector which outperforms both model-free baselines and strong classifiers based on quality estimation or large pre-trained models on manually annotated English-Chinese and German-English translation test beds.
more »
« less
- Award ID(s):
- 1750695
- PAR ID:
- 10520446
- Publisher / Repository:
- Association for Computational Linguistics
- Date Published:
- Journal Name:
- Transactions of the Association for Computational Linguistics
- Volume:
- 11
- ISSN:
- 2307-387X
- Page Range / eLocation ID:
- 546 to 564
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Large Language Models (LLMs) have demonstrated significant potential across various applications, but their use as AI copilots in complex and specialized tasks is often hindered by AI hallucinations, where models generate outputs that seem plausible but are incorrect. To address this challenge, we develop AutoFEA, an intelligent system that integrates LLMs with Finite Element Analysis (FEA) to automate the generation of FEA input files. Our approach features a novel planning method and a graph convolutional network (GCN)-Transformer Link Prediction retrieval model, which enhances the accuracy and reliability of the generated simulations. The AutoFEA system proceeds with key steps: dataset preparation, step-by-step planning, GCN-Transformer Link Prediction retrieval, LLM-driven code generation, and simulation using CalculiX. In this workflow, the GCN-Transformer model predicts and retrieves relevant example codes based on relationships between different steps in the FEA process, guiding the LLM in generating accurate simulation codes. We validate AutoFEA using a specialized dataset of 512 meticulously prepared FEA projects, which provides a robust foundation for training and evaluation. Our results demonstrate that AutoFEA significantly reduces AI hallucinations by grounding LLM outputs in physically accurate simulation data, thereby improving the success rate and accuracy of FEA simulations and paving the way for future advancements in AI-assisted engineering tasks.more » « less
-
With their increased capability, AI-based chatbots have become increasingly popular tools to help users answer complex queries. However, these chatbots may hallucinate, or generate incorrect but very plausible-sounding information, more frequently than previously thought. Thus, it is crucial to examine strategies to mitigate human susceptibility to hallucinated output. In a between-subjects experiment, participants completed a difficult quiz with assistance from either a polite or neutral-toned AI chatbot, which occasionally provided hallucinated (incorrect) information. Signal detection analysis revealed that participants interacting with polite-AI showed modestly higher sensitivity in detecting hallucinations and a more conservative response bias compared to those interacting with neutral-toned AI. While the observed effect sizes were modest, even small improvements in users’ ability to detect AI hallucinations can have significant consequences, particularly in high-stakes domains or when aggregated across millions of AI interactions.more » « less
-
Recent language models generate false but plausible-sounding text with surprising frequency. Such “hallucinations” are an obstacle to the usability of language-based AI systems and can harm people who rely upon their outputs. This work shows that there is an inherent statistical lower-bound on the rate that pretrained language models hallucinate certain types of facts, having nothing to do with the transformer LM architecture or data quality. For “arbitrary” facts whose veracity cannot be determined from the training data, we show that hallucinations must occur at a certain rate for language models that satisfy a statistical calibration condition appropriate for generative language models. Specifically, if the maximum probability of any fact is bounded, we show that the probability of generating a hallucination is close to the fraction of facts that occur exactly once in the training data (a “Good-Turing” estimate), even assuming ideal training data without errors. One conclusion is that models pretrained to be sufficiently good predictors (i.e., calibrated) may require post-training to mitigate hallucinations on the type of arbitrary facts that tend to appear once in the training set. However, our analysis also suggests that there is no statistical reason that pretraining will lead to hallucination on facts that tend to appear more than once in the training data (like references to publications such as articles and books, whose hallucinations have been particularly notable and problematic) or on systematic facts (like arithmetic calculations). Therefore, different architectures and learning algorithms may mitigate these latter types of hallucinations.more » « less
-
Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes re- mains a significant challenge. We address this by introducing XplainLLM, a dataset accom- panying an explanation framework designed to enhance LLM transparency and reliability. Our dataset comprises 24,204 instances where each instance interprets the LLM’s reasoning behavior using knowledge graphs (KGs) and graph attention networks (GAT), and includes explanations of LLMs such as the decoder- only Llama-3 and the encoder-only RoBERTa. XplainLLM also features a framework for gener- ating grounded explanations and the debugger- scores for multidimensional quality analysis. Our explanations include why-choose and why- not-choose components, reason-elements, and debugger-scores that collectively illuminate the LLM’s reasoning behavior. Our evaluations demonstrate XplainLLM’s potential to reduce hallucinations and improve grounded explana- tion generation in LLMs. XplainLLM is a re- source for researchers and practitioners to build trust and verify the reliability of LLM outputs. Our code and dataset are publicly available.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1162/tacl_a_00563
