Retrieval-Augmented Generation (RAG) has emerged as a crucial method for addressing hallucinations in large language models (LLMs). While recent research has extended RAG models to complex noisy scenarios, these explorations often confine themselves to limited noise types and presuppose that noise is inherently detrimental to LLMs, potentially deviating from real-world retrieval environments and restricting practical applicability. In this paper, we define seven distinct noise types from a linguistic perspective and establish a Noise RAG Benchmark (NoiserBench), a comprehensive evaluation framework encompassing multiple datasets and reasoning tasks. Through empirical evaluation of eight representative LLMs with diverse architectures and scales, we reveal that these noises can be further categorized into two practical groups: noise that is beneficial to LLMs (aka beneficial noise) and noise that is harmful to LLMs (aka harmful noise). While harmful noise generally impairs performance, beneficial noise may enhance several aspects of model capabilities and overall performance. Our analysis offers insights for developing robust RAG solutions and mitigating hallucinations across diverse retrieval scenarios. Code is available at https://github.com/jinyangwu/NoiserBench.

The ability to comprehend human emotion using multimodal large language models (MLLMs) is essential for advancing human-AI interaction and multimodal sentiment analysis. While psychology theory-based human annotations have contributed to multimodal emotion tasks, the subjective nature of emotional perception often leads to inconsistent annotations, limiting the robustness of current models. Addressing these challenges requires more fine-grained methods and evaluation frameworks. In this paper, we propose the Retrieval-Augmented Emotion Reasoning (RAER) framework, a plug-and-play module that enhances MLLMs’ ability to tackle compound and context-rich emotion tasks. To systematically evaluate model performance, we introduce the Stimulus-Armed Bandit (SAB) framework, designed to benchmark emotional reasoning capabilities. Additionally, we construct the Compound Emotion QA dataset, an AI-generated multimodal dataset aimed at strengthening emotion understanding in MLLMs. Experimental results demonstrate the effectiveness of RAER across both traditional benchmarks and SAB evaluations, highlighting its potential to enhance emotional intelligence in multimodal AI systems.

“Recent advancements in neural speech synthesis technologies have brought aboutwidespread applications but have also raised concerns about potential misuse and abuse.Addressing these challenges is crucial, particularly in the realms of forensics and intellec-tual property protection. While previous research on source attribution of synthesizedspeech has its limitations, our study aims to fill these gaps by investigating the identifi-cation of sources in synthesized speech. We focus on analyzing speech synthesis modelfingerprints in generated speech waveforms, emphasizing the roles of the acoustic modeland vocoder. Our research, based on the multi-speaker LibriTTS dataset, reveals twokey insights: (1) both vocoders and acoustic models leave distinct, model-specific fin-gerprints on generated waveforms, and (2) vocoder fingerprints, being more dominant,may obscure those from the acoustic model. These findings underscore the presence ofmodel-specific fingerprints in both components, suggesting their potential significance insource identification applications.”

“To enhance the effectiveness of fake audio detection techniques, researchers have developed mul-tiple datasets such as those for the ASVspoof and ADD challenges. These datasets typically focuson capturing non-emotional characteristics in speech, such as the identity of the speaker and theauthenticity of the content. However, they often overlook changes in the emotional state of theaudio, which is another crucial dimension affecting the authenticity of speech. Therefore, thisstudy reports our progress in developing such an emotion fake audio detection dataset involvingchanging emotion state of the origin audio named EmoFake. The audio samples in EmoFake aregenerated using open-source emotional voice conversion models, intended to simulate potentialemotional tampering scenarios in real-world settings. We conducted a series of benchmark ex-periments on this dataset, and the results show that even advanced fake audio detection modelstrained on the ASVspoof 2019 LA dataset and the ADD 2022 track 3.2 dataset face challengeswith EmoFake. The EmoFake is publicly available1 now.”

The pre-trained language model (PLM) has achieved significant success in the field of knowledge graph completion (KGC) by effectively modeling entity and relation descriptions. In recent studies, the research in this field has been categorized into methods based on word matching and sentence matching, with the former significantly lags behind. However, there is a critical issue in word matching methods, which is that these methods fail to obtain satisfactory single embedding representations for entities.To address this issue and enhance entity representation, we propose the Bilateral Masking with prompt for Knowledge Graph Completion (BMKGC) approach.Our methodology employs prompts to narrow the distance between the predicted entity and the known entity. Additionally, the BMKGC model incorporates a bi-encoder architecture, enabling simultaneous predictions at both the head and tail. Furthermore, we propose a straightforward technique to augment positive samples, mitigating the problem of degree bias present in knowledge graphs and thereby improving the model’s robustness. Experimental results conclusively demonstrate that BMKGC achieves state-of-the-art performance on the WN18RR dataset.

Pre-trained Language Models (PLMs) like BERT have achieved superior performance on different downstream tasks, even when such a model is trained on a general domain. Moreover, recent studies have shown that continued pre-training on task-specific data, known as task adaptive pre-training (TAPT), can further improve downstream task performance. However, conventional TAPT adjusts all the parameters of the PLMs, which distorts the learned generic knowledge embedded in the original PLMs weights, and it is expensive to store a whole model copy for each downstream task. In this paper, we propose NLoPT, a two-step n-gram enhanced low-rank task adaptive pre-training method, to effectively and efficiently customize a PLM to the downstream task. Specifically, we first apply low-rank adaption (LoRA), a prevalent parameter-efficient technique, for efficient TAPT. We further explicitly incorporate the task-specific multi-granularity n-gram information via the cross-attention mechanism. Experimental results on six datasets from four domains illustrate the effectiveness of NLoPT, demonstrating the superiority of LoRA based TAPT and the necessity of incorporating task-specific n-gram information.