Retrieval-augmented generation (RAG) leverages the strengths of information retrieval and generative models to enhance the handling of real-time and domain-specific knowledge. Despite its advantages, limitations within RAG components may cause hallucinations, or more precisely termed confabulations in generated outputs, driving extensive research to address these limitations and mitigate hallucinations. This review focuses on hallucination in retrieval-augmented large language models (LLMs). We first examine the causes of hallucinations from different sub-tasks in the retrieval and generation phases. Then, we provide a comprehensive overview of corresponding hallucination mitigation techniques, offering a targeted and complete framework for addressing hallucinations in retrieval-augmented LLMs. We also investigate methods to reduce the impact of hallucination through detection and correction. Finally, we discuss promising future research directions for mitigating hallucinations in retrieval-augmented LLMs.

Crowdsourcing systems provide a cost effective and convenient way to collect labels, but they often fail to guarantee the quality of the labels. This paper proposes a novel framework that introduces noise correction techniques to further improve the quality of integrated labels that are inferred from the multiple noisy labels of objects. In the proposed general framework, information about the qualities of labelers estimated by a front-end ground truth inference algorithm is utilized to supervise subsequent label noise filtering and correction. The framework uses a novel algorithm termed adaptive voting noise correction (AVNC) to precisely identify and correct the potential noisy labels. After filtering out the instances with noisy labels, the remaining cleansed data set is used to create multiple weak classifiers, based on which a powerful ensemble classifier is induced to correct these noises. Experimental results on eight simulated data sets with different kinds of features and two real-world crowdsourcing data sets in different domains consistently show that: 1) the proposed framework can improve label quality regardless of inference algorithms, especially under the circumstance that each instance has a few repeated labels and 2) since the proposed AVNC algorithm considers both the number of and the probability of potential label noises, it outperforms the state-of-the-art noise correction algorithms.

Due to low quality of crowdsourced labelers, the integrated label of each example is usually inferred from its multiple noisy labels provided by different labelers. This paper proposes a novel algorithm, Ground Truth Inference using Clustering (GTIC), to improve the quality of integrated labels for multi-class labeling. For a K labeling case, GTIC utilizes the multiple noisy label sets of examples to generate features. Then, it uses a K-Means algorithm to cluster all examples into K different groups, each of which is mapped to a specific class. Examples in the same cluster are assigned a corresponding class label. We compare GTIC with four existing multi-class ground truth inference algorithms, majority voting (MV), Dawid & Skene's (DS), ZenCrowd (ZC) and Spectral DS (SDS), on one synthetic and eight real-world datasets. Experimental results show that the performance of GTIC is significantly superior to the others in terms of both accuracy and M-AUC. Besides, the running time of GTIC is about twenty times faster than EM-based complicated inference algorithms.

With the crowdsourcing of small tasks becoming easier, it is possible to obtain non-expert/imperfect labels at low cost. With low-cost imperfect labeling, it is straightforward to collect multiple labels for the same data items. This paper proposes strategies of utilizing these multiple labels for supervised learning, based on two basic ideas: majority voting and pairing. We show several interesting results based on our experiments. (i) The strategies based on the majority voting idea work well under the situation where the certainty level is high. (ii) On the contrary, the pairing strategies are more preferable under the situation where the certainty level is low. (iii) Among the majority voting strategies, soft majority voting can reduce the bias and roughness, and perform better than majority voting. (iv) Pairing can completely avoid the bias by having both sides (potentially correct and incorrect/noisy information) considered. Beta estimation is applied to reduce the impact of the noise in pairing. Our experimental results show that pairing with Beta estimation always performs well under different certainty levels. (v) All strategies investigated are labeling quality agnostic strategies for real-world applications, and some of them perform better than or at least very close to the gnostic strategies.

It can be easy to collect multiple noisy labels for the same object via Internet-based crowdsourcing systems. Labelers may have bias when labeling, due to lacking expertise, dedication, and personal preference. These cause Imbalanced Multiple Noisy Labeling. In most cases, we have no information about the labeling qualities of labelers and the underlying class distributions. It is important to design agnostic solutions to utilize these noisy labels for supervised learning. We first investigate how imbalanced multiple noisy labeling affects the class distributions of training sets and the performance of classification. Then, an agnostic algorithm Positive LAbel frequency Threshold (PLAT) is proposed to deal with the imbalanced labeling issue. Simulations on eight UCI data sets with different underlying class distributions show that PLAT not only effectively deals with the imbalanced multiple noisy labeling problems that off-the-shelf agnostic methods cannot cope with, but also performs nearly the same as majority voting under the circumstances without imbalance. We also apply PLAT to eight real-world data sets with imbalanced labels collected from Amazon Mechanical Turk, and the experimental results show that PLAT is efficient and better than other ground truth inference algorithms.