论文检索

Andrei-Marius Avram, Bănescu Ema-Ioana, Anda-Teodora Robea, Dumitru-Clementin Cercel, Mihaela-Claudia Cercel

This paper introduces MoRoVoc, the largest dataset for analyzing the regional variation of spoken Romanian. It has more than 93 hours of audio and 88,192 audio samples, balanced between the Romanian language spoken in Romania and the Republic of Moldova. We further propose a multi-target adversarial training framework for speech models that incorporates demographic attributes (i.e., age and gender of the speakers) as adversarial targets, making models discriminative for primary tasks while remaining invariant to secondary attributes. The adversarial coefficients are dynamically adjusted via meta-learning to optimize performance. Our approach yields notable gains: Wav2Vec2-Base achieves 78.21% accuracy for the variation identification of spoken Romanian using gender as an adversarial target, while Wav2Vec2-Large reaches 93.08% accuracy for gender classification when employing both dialect and age as adversarial objectives.

Enshi Zhang, Christian Poellabauer

Clinical interviews are a standard method for assessing depression. Recent approaches have improved prediction accuracy by focusing on specific questions posed by the interviewer and manually selected question-answer (QA) pairs that target mental health content. However, these methods often neglect the broader conversational context, resulting in limited generalization and reduced robustness, particularly in less structured interviews, which are common in real-world clinical settings. In this work, we develop a multimodal dialogue-level transformer that captures the dynamics of dialogue within each interview by using a combination of sequential positional embedding and question context vectors. In addition to the depression prediction branch, we build an adversarial classifier with a gradient reversal layer to learn shared representations that remain invariant to the types of questions asked during the interview. This approach aims to reduce biased learning and improve the fairness and generalizability of depression detection in diverse clinical interview scenarios. Classification and regression experiments conducted on three real-world interview-based datasets and one synthetic dataset demonstrate the robustness and generalizability of our model.

Mingsheng Cai, Jiuming Jiang, Wenhao Huang, Che Liu, Rossella Arcucci

Cardiovascular diseases are a leading cause of death and disability worldwide. Electrocardiogram (ECG) is critical for diagnosing and monitoring cardiac health, but obtaining large-scale annotated ECG datasets is labor-intensive and time-consuming. Recent ECG Self-Supervised Learning (eSSL) methods mitigate this by learning features without extensive labels but fail to capture fine-grained clinical semantics and require extensive task-specific fine-tuning. To address these challenges, we propose \textbf{SuPreME}, a \textbf{Su}pervised \textbf{Pre}-training framework for \textbf{M}ultimodal \textbf{E}CG representation learning. SuPreME is pre-trained using structured diagnostic labels derived from ECG report entities through a one-time offline extraction with Large Language Models (LLMs), which help denoise, standardize cardiac concepts, and improve clinical representation learning. By fusing ECG signals with textual cardiac queries instead of fixed labels, SuPreME enables zero-shot classification of unseen conditions without further fine-tuning. We evaluate SuPreME on six downstream datasets covering 106 cardiac conditions, achieving superior zero-shot AUC performance of 77.20%, surpassing state-of-the-art eSSLs by 4.98%. Results demonstrate SuPreME’s effectiveness in leveraging structured, clinically relevant knowledge for high-quality ECG representations.

Erfan Zinvandi, Morteza Alikhani, Mehran Sarmadi, Zahra Pourbahman, Sepehr Arvin, Reza Kazemi, Arash Amini

In this paper, we introduce a comprehensive benchmark for Persian (Farsi) text embeddings, built upon the Massive Text Embedding Benchmark (MTEB). Our benchmark includes 63 datasets spanning seven different tasks: classification, clustering, pair classification, reranking, retrieval, summary retrieval, and semantic textual similarity. The datasets are a combination of existing, translated, and newly generated (synthetic) data, offering a diverse and robust evaluation framework for Persian language models. All newly translated and synthetic datasets were rigorously evaluated by both humans and automated systems to ensure high quality and reliability. Given the growing adoption of text embedding models in chatbots, evaluation datasets are becoming an essential component of chatbot development and Retrieval-Augmented Generation (RAG) systems. As a contribution, we include chatbot evaluation datasets in the MTEB benchmark for the first time. Additionally, we introduce the novel task of summary retrieval, which is not included in the standard MTEB tasks. Another key contribution of this work is the introduction of a substantial number of new Persian-language NLP datasets for both training and evaluation, many of which have no existing counterparts in Persian. We evaluate the performance of several Persian and multilingual embedding models across a wide range of tasks. This work presents an open-source benchmark with datasets, accompanying code, and a public leaderboard.

Xueyi Zhou, Qi Lu, Dong-Kyu Chae

Existing Artificial Olfaction (AO) primarily serves two tasks: Odor Classification (OC) and Odor Source Localization (OSL). Both tasks w.r.t. indoor event detection scenarios are studied either using a single electronic nose (e-nose) mounted on the ceiling or mobile robot(s) equipped with e-noses. However, they are not compatible with smart home scenarios due to diverse obstacles (e.g., chairs and tables) and the need for natural interaction. In this paper, we explore the feasibility and usability of a Conversational Interfaces for Artificial Olfaction (CIAO) system using Large Language Models (LLMs) in Smart Home. We made the first olfaction-oriented corpus for LLM evaluation, as well as an olfaction dataset via a self-developed olfactory sensory network. We train the dedicated models for OSL and OC using the dataset and integrate them into a tool within the MCP (Model Context Protocol) server. Five commercial LLMs are used as MCP clients for experiments and validation. Our experimental results indicate that our CIAO system is technically feasible and applicable. Besides, we observe that ChatGPT-4o relatively outperforms in terms of both answer quality and overall LLM usability in pervasive IoT scenarios. Qwen-Plus, in contrast, appears to be a promising solution for robot-compatible applications. To our knowledge, this work is the first effort to bring forward conversational interfaces for AO, enabling multi-turn conversations with contexts beyond one-off question answering. Our codes and partial corpus are available at https://github.com/HokyeeJau/CIAO.

Sunwoo Kim, Soo Yong Lee, Jaemin Yoo, Kijung Shin

While graph neural networks (GNNs) have shown remarkable performance across diverse graph-related tasks, their high-dimensional hidden representations render them black boxes. In this work, we propose Graph Lingual Network (GLN), a GNN built on large language models (LLMs), with hidden representations in the form of human-readable text. Through careful prompt design, GLN incorporates not only the message passing module of GNNs but also advanced GNN techniques, including graph attention and initial residual connection. The comprehensibility of GLN’s hidden representations enables an intuitive analysis of how node representations change (1) across layers and (2) under advanced GNN techniques, shedding light on the inner workings of GNNs. Furthermore, we demonstrate that GLN achieves strong zero-shot performance on node classification and link prediction, outperforming existing LLM-based baseline methods.

Zhu Wang, Homaira Huda Shomee, Sathya N. Ravi, Sourav Medya

In the field of design patent analysis, traditional tasks such as patent classification and patent image retrieval heavily depend on the image data. However, patent images—typically consisting of sketches with abstract and structural elements of an invention—often fall short in conveying comprehensive visual context and semantic information. This inadequacy can lead to ambiguities in evaluation during prior art searches. Recent advancements in vision-language models, such as CLIP, offer promising opportunities for more reliable and accurate AI-driven patent analysis. In this work, we leverage CLIP models to develop a unified framework DesignCLIP for design patent applications with a large-scale dataset of U.S. design patents. To address the unique characteristics of patent data, DesignCLIP incorporates class-aware classification and contrastive learning, utilizing generated detailed captions for patent images and multi-views image learning. We validate the effectiveness of DesignCLIP across various downstream tasks, including patent classification and patent retrieval. Additionally, we explore multimodal patent retrieval, which provides the potential to enhance creativity and innovation in design by offering more diverse sources of inspiration. Our experiments show that DesignCLIP consistently outperforms baseline and SOTA models in the patent domain on all tasks. Our findings underscore the promise of multimodal approaches in advancing patent analysis. The codebase is available here: https://github.com/AI4Patents/DesignCLIP.

Yinghao Song, Xiangji Zeng, Shuai Cui, Lu Sun, Zhaowei Liu, Yuan Yuan, Yulu Wang, Hai Zhou, Zhaohan Gong

With the commercialization of short video platforms (SVPs), the demand for compliance auditing of advertising content has grown rapidly. The rise of large vision-language models (VLMs) offers new opportunities for automating ad content moderation. However, short video advertising scenarios present unique challenges due to \textbf{data drift (DD)} and \textbf{label drift (LD)}. DD refers to rapid shifts in data distribution caused by advertisers to evade platform review mechanisms. LD arises from the evolving and increasingly standardized review guidelines of SVPs, which effectively alter the classification boundaries over time. Despite the significance of these phenomena, there is currently a lack of benchmark tools designed to evaluate model performance under such conditions. To address this gap, we propose \textbf{AdDriftBench (ADB)}. The ADB dataset consists of 3,480 short video ads, including 2,280 examples labeled under data drift scenarios, designed to evaluate the generalization capabilities of VLMs under rapidly shifting content distributions. An additional 1,200 examples represent label drift scenarios, aimed at assessing VLMs’ abilities in instruction following and fine-grained semantic understanding under varying auditing standards. Through extensive experiments on 16 open-source VLMs, we find that current models perform moderately in short video advertising contexts, particularly in handling fine-grained semantics and adapting to shifting instructions. Our dataset will be made publicly available.

Alberto Muñoz-Ortiz, David Vilares, Caio Corro, Carlos Gómez-Rodríguez

We cast nested named entity recognition (NNER) as a sequence labeling task by leveraging prior work that linearizes constituency structures, effectively reducing the complexity of this structured prediction problem to straightforward token classification. By combining these constituency linearizations with pretrained encoders, our method captures nested entities while performing exactly n tagging actions. Our approach achieves competitive performance compared to less efficient systems, and it can be trained using any off-the-shelf sequence labeling library.

Dongyu Zhang, Qingqing Hong, Bingxuan Hou, Jiayi Lin, Chenyang Zhang, Jialin Li, Junli Wang

Large language models are prone to generating hallucination that deviates from factual information. Existing studies mainly focus on detecting the presence of hallucinations but lack a systematic classification approach, which hinders deeper exploration of their characteristics. To address this, we introduce the concept of belief state, which quantifies the model’s confidence in its own responses. We define the belief state of the model based on self-consistency, leveraging answer repetition rates to label confident and uncertain states. Based on this, we categorize factuality hallucination into two types: Overconfident Hallucination and Unaware Hallucination. Furthermore, we propose BAFH, a factuality hallucination type detection method. By training a classifier on model’s hidden states, we establish a link between hidden states and belief states, enabling efficient and automatic hallucination type detection. Experimental results demonstrate the effectiveness of BAFH and the differences between hallucination types.

Joykirat Singh, Subhabrata Dutta, Tanmoy Chakraborty

Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the generative prior using in-context examples. However, spurious features learned from noisy data hinder their generalizability. Supervised fine-tuning can enhance task specificity but may lead to data inefficiency. Prior studies indicate that (i) noisy neural circuitries coexist with generalizable ones within LLMs, and (ii) finetuning typically enhances (or suppresses) existing abilities without introducing newer ones. Building upon these, we propose TaRot, a novel method for task adaptation. TaRot intervenes in the neural circuitries using learnable rotation matrices that are optimized using Bayesian optimization, on labelled samples in the order of standard few-shot prompting examples. Experiments on multiple classification and generation tasks using LLMs of varying sizes reveal the efficacy of TaRot, improving upon both zero- as well as few-shot performance, with average improvements (across models and tasks) of 15.6% and 14%, respectively.

Mehmet Selman Baysan, Tunga Gungor

We introduce TR-MTEB, the first large-scale, task-diverse benchmark designed to evaluate sentence embedding models for Turkish. Covering six core tasks as classification, clustering, pair classification, retrieval, bitext mining, and semantic textual similarity, TR-MTEB incorporates 26 high-quality datasets, including native and translated resources. To complement this benchmark, we construct a corpus of 34.2 million weakly supervised Turkish sentence pairs and train two Turkish-specific embedding models using contrastive pretraining and supervised fine-tuning. Evaluation results show that our models, despite being trained on limited resources, achieve competitive performance across most tasks and significantly improve upon baseline monolingual models. All datasets, models, and evaluation pipelines are publicly released to facilitate further research in Turkish natural language processing and low-resource benchmarking.

Mengting Hu, Jianfeng Wu, Ming Jiang, Yalan Xie, Zhunheng Wang, Rui Ying, Xiaoyi Liu, Ruixuan Xu, Hang Gao, Renhong Cheng

Few-shot relation classification aims to recognize the relation between two mentioned entities, with the help of only a few support samples. However, a few samples tend to be limited for tackling unlimited queries. If a query cannot find references from the support samples, it is defined as none-of-the-above (NOTA). Previous works mainly focus on how to distinguish N+1 categories, including N known relations and one NOTA class, to accurately recognize relations. However, the robustness towards various NOTA rates, i.e. the proportion of NOTA among queries, is under investigation. In this paper, we target the robustness and propose a simple but effective framework. Specifically, we introduce relation descriptions as external knowledge to enhance the model’s comprehension of the relation semantics. Moreover, we further promote robustness by proposing a novel agreement loss. It is designed for seeking decision consistency between the instance-level decision, i.e. support samples, and relation-level decision, i.e. relation descriptions. Extensive experimental results demonstrate that the proposed framework outperforms strong baselines while being robust against various NOTA rates. The code is released on GitHub at https://github.com/Pisces-29/RoFRC.

Jie Zhao, Wanting Ning, Yuxiao Fei, Yubo Feng, Lishuang Li

In Natural Language Processing(NLP), Event Temporal Relation Extraction (ETRE) is to recognize the temporal relations of two events. Prior studies have noted the importance of language models for ETRE. However, the restricted pre-trained knowledge of Small Language Models(SLMs) limits their capability to handle minority class relations in imbalanced classification datasets. For Large Language Models(LLMs), researchers adopt manually designed prompts or instructions, which may introduce extra noise, leading to interference with the model’s judgment of the long-distance dependencies between events. To address these issues, we propose GDLLM, a Global Distance-aware modeling approach based on LLMs. We first present a distance-aware graph structure utilizing Graph Attention Network(GAT) to assist the LLMs in capturing long-distance dependency features. Additionally, we design a temporal feature learning paradigm based on soft inference to augment the identification of relations with a short-distance proximity band, which supplements the probabilistic information generated by LLMs into the multi-head attention mechanism. Since the global feature can be captured effectively, our framework substantially enhances the performance of minority relation classes and improves the overall learning ability. Experiments on two publicly available datasets, TB-Dense and MATRES, demonstrate that our approach achieves state-of-the-art (SOTA) performance.

Yutong Gao, Maoyuan Shao, Xinyang Huang, Chuang Zhu, Yu Weng, Xuan Liu, Lijuan Sun, Guoshun Nan

CLIP’s success has demonstrated that prompt tuning can achieve robust cross-modal semantic alignment for tasks ranging from open-domain recognition to fine-grained classification. However, redundant or weakly relevant feature components introduce noise and incur unnecessary computational costs. In this work, we propose Spotlighter, a lightweight token-selection framework that simultaneously enhances accuracy and efficiency in prompt tuning. Spotlighter evaluates each visual token’s activation from both sample-wise and semantic-wise perspectives and retains only the top-scoring tokens for downstream prediction. A class-specific semantic memory bank of learned prototypes refines this selection, ensuring semantic representativeness and compensating for discarded features. To further prioritize informative signals, we introduce a two-level ranking mechanism that dynamically weights token–prototype interactions. Across 11 few-shot benchmarks, Spotlighter outperforms CLIP by up to 11.19% in harmonic mean accuracy and achieves up to 0.8K additional FPS, with only 21 extra parameters. These results establish Spotlighter as an effective and scalable baseline for prompt tuning.

Abhijit Chakraborty, Chahana Dahal, Vivek Gupta

Federated Retrieval-Augmented Generation (Federated RAG) combines Federated Learning (FL),which enables distributed model training without exposing raw data, with Retrieval-Augmented Generation (RAG), which improves the factual accuracy of language models by grounding outputs in external knowledge. As large language models are increasingly deployed in privacy-sensitive domains such as healthcare, finance, and personalized assistance, Federated RAG offers a promising framework for secure, knowledge-intensive natural language processing (NLP). To the best of our knowledge, this paper presents the first systematic mapping study of Federated RAG, covering literature published between 2020 and 2025. Following Kitchenham’s guidelines for evidence-based software engineering, we develop a structured classification of research focuses, contribution types, and application domains. We analyze architectural patterns, temporal trends, and key challenges, including privacy-preserving retrieval, cross-client heterogeneity, and evaluation limitations. Our findings synthesize a rapidly evolving body of research, identify recurring design patterns, and surface open questions, providing a foundation for future work at the intersection of RAG and federated systems.

Che Liu, Cheng Ouyang, Zhongwei Wan, Haozhe Wang, Wenjia Bai, Rossella Arcucci

Recent advancements in multimodal representation learning for electrocardiogram (ECG) have moved onto learning representations by aligning ECG signals with their paired free-text reports. However, current methods often result in suboptimal alignment of ECG signals with their corresponding text reports, thereby limiting diagnostic accuracy. This is primarily due to the complexity and unstructured nature of medical language, which makes it challenging to effectively align ECG signals with the corresponding text reports. Additionally, these methods are unable to handle arbitrary combinations of ECG leads as inputs, which poses a challenge since 12-lead ECGs may not always be available in under-resourced clinical environments.In this work, we propose the **Knowledge-enhanced Multimodal ECG Representation Learning (K-MERL)** framework to address these challenges. K-MERL leverages large language models (LLMs) to extract structured knowledge from free-text reports, enhancing the effectiveness of ECG multimodal learning. Furthermore, we design a lead-aware ECG encoder to capture lead-specific spatial-temporal characteristics of 12-lead ECGs, with dynamic lead masking. This novel encoder allows our framework to handle arbitrary lead inputs, rather than being limited to a fixed set of full 12 leads, which existing methods necessitate.We evaluate K-MERL on six external ECG datasets and demonstrate its superior capability. K-MERL not only outperforms all existing methods in zero-shot classification and linear probing tasks using 12 leads, but also achieves state-of-the-art (SOTA) results in partial-lead settings, with an average improvement of **16%** in AUC score on zero-shot classification compared to previous SOTA multimodal methods. All data and code will be released upon acceptance.

Leslie Barrett, Vikram Sunil Bajaj, Robert John Kingan

Anomaly detection (AD), also known as Outlier Detection, is a longstanding problem in machine learning, which has recently been applied to text data. In these datasets, a textual anomaly is a part of the text that does not fit the overall topic of the text. Some recent approaches to textual AD have used transformer models, achieving positive results but with trade-offs in pre-training time and inflexibility with respect to new domains. Others have used linear models which are fast and more flexible but not always competitive on certain datasets. We introduce a new approach based on Large Pre-trained Language Models in three modalities. Our findings indicate that LLMs beat baselines when AD is presented as an imbalanced classification problem regardless of the concentration of anomalous samples. However, their performance is markedly worse on unsupervised AD, suggesting that the concept of “anomaly” may somehow elude the LLM reasoning process.

Wei Jie Yeo, Nirmalendu Prakash, Clement Neo, Ranjan Satapathy, Roy Ka-Wei Lee, Erik Cambria

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify latent features that causally mediate refusal behaviors. We apply our method to two open-source chat models and intervene on refusal-related features to assess their influence on generation, validating their behavioral impact across multiple harmful datasets. This enables a fine-grained inspection of how refusal manifests at the activation level and addresses key research questions such as investigating upstream-downstream latent relationship and understanding the mechanisms of adversarial jailbreaking techniques. We also establish the usefulness of refusal features in enhancing generalization for linear probes to out-of-distribution adversarial samples in classification tasks.

Yuchen Yan, Aakash Kolekar, Sahika Genc, Wenju Xu, Edward W Huang, Anirudh Srinivasan, Mukesh Jain, Qi He, Hanghang Tong

Recently, textual graph-based retrieval-augmented generation (GraphRAG) has gained popularity for addressing hallucinations in large language models when answering domain-specific questions. Most existing studies assume that generated answers should comprehensively integrate all relevant information from the textual graph. However, this assumption may not always hold when certain information needs to be vetted or even blocked (e.g., due to safety concerns). In this paper, we target two sides of textual graph understanding and question answering: (1) normal question Answering (A-side): following standard practices, this task generates accurate responses using all relevant information within the textual graph; and (2) Blocked question answering (B-side): A new paradigm where the GraphRAG model must effectively infer and exclude specific relevant information in the generated response. To address these dual tasks, we propose TAONA, a novel GraphRAG model with two variants: (1) TAONA-A for A-side task, which incorporates a specialized GraphEncoder to learn graph prompting vectors; and (2) TAONA-B for B-side task, employing semi-supervised node classification to infer potential blocked graph nodes. Extensive experiments validate TAONA’s superior performance for both A-side and B-side tasks.