Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Antinuclear antibody (ANA) testing is a critical method for diagnosing autoimmune disorders such as Lupus, Sjögren's syndrome, and scleroderma. Despite its importance, manual ANA detection is slow, labor-intensive, and demands years of training. ANA detection is complicated by over 100 coexisting antibody types, resulting in vast fluorescent pattern combinations. Although machine learning and deep learning have enabled automation, ANA detection in real-world clinical settings presents unique challenges as it involves multi-instance, multi-label (MIML) learning. In this paper, a novel framework for ANA detection is proposed that handles the complexities of MIML tasks using unaltered microscope images without manual preprocessing. Inspired by human labeling logic, it identifies consistent ANA sub-regions and assigns aggregated labels accordingly. These steps are implemented using three task-specific components: an instance sampler, a probabilistic pseudo-label dispatcher, and self-paced weight learning rate coefficients. The instance sampler suppresses low-confidence instances by modeling pattern confidence, while the dispatcher adaptively assigns labels based on instance distinguishability. Self-paced learning adjusts training according to empirical label observations. Our framework overcomes limitations of traditional MIML methods and supports end-to-end optimization. Extensive experiments on one ANA dataset and three public medical MIML benchmarks demonstrate the superiority of our framework. On the ANA dataset, our model achieves up to +7.0% F1-Macro and +12.6% mAP gains over the best prior method, setting new state-of-the-art results. It also ranks top-2 across all key metrics on public datasets, reducing Hamming loss and one-error by up to 18.2% and 26.9%, respectively. The source code can be accessed at https://github.com/fletcherjiang/ANA-SelfPacedLearning.

Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Ye Qi, Zhicheng Dou. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations.Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still face several limitations: additional deployment costs of separate retrievers, redundant input tokens from retrieved text chunks, and the lack of joint optimization of retrieval and generation.To address these issues, we propose RetroLLM, a unified framework that integrates retrieval and generation into a single, auto-regressive process, enabling LLMs to directly generate fine-grained evidence from the corpus with constrained decoding.Moreover, to mitigate false pruning in the process of constrained evidence generation, we introduce (1) hierarchical FM-Index constraints, which generate corpus-constrained clues to identify a subset of relevant documents before evidence generation, reducing irrelevant decoding space; and (2) a forward-looking constrained decoding strategy, which considers the relevance of future sequences to improve evidence accuracy.Extensive experiments on five open-domain QA datasets demonstrate RetroLLM's superior performance across both in-domain and out-ofdomain tasks.The code is available at https: //github.com/sunnynexus/RetroLLM.

Conversational Retrieval-Augmented Generation (RAG) systems enhance user interactions by integrating large language models (LLMs) with external knowledge retrieval. However, multi-turn conversations present significant challenges, including implicit user intent and noisy context, which hinder accurate retrieval and response generation. Existing approaches often struggle with the unstructured conversational context and fail to model explicit relations among conversational turns. Moreover, they do not leverage historically relevant passages effectively. To overcome these limitations, we propose EvoRAG, a novel framework that maintains an evolving knowledge graph aligned with the unstructured conversational context. This graph explicitly captures relations among user queries, system responses, and relevant passages across conversational turns, serving as a structured representation of the context. EvoRAG includes three key components: (1) a dual-path retrieval module for context denoising, (2) a unified knowledge integration module for query rewriting and summarization, and (3) a graph-enhanced RAG module for accurate retrieval and response generation. Experiments on four public conversational RAG datasets show that EvoRAG significantly outperforms strong baselines, particularly in handling topic shifts and long dialogue contexts.

Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive tasks and hinders their ability to produce comprehensive research reports requiring synthesis of diverse web information. To address this, we propose WebThinker, a deep research agent that empowers LRMs to autonomously search the web, navigate among web pages, and draft reports during the reasoning process. WebThinker integrates a Deep Web Explorer module, enabling LRMs to dynamically search, navigate, and extract information from the web when encountering knowledge gaps. It also employs an Autonomous Think-Search-and-Draft strategy, allowing the model to seamlessly interleave reasoning, information gathering, and report writing in real time. To further enhance research tool utilization, we introduce an RL-based training strategy via iterative online Direct Preference Optimization (DPO). Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems. Our approach enhances LRM reliability and applicability in complex scenarios, paving the way for more capable and versatile deep research systems. The code is available at https://github.com/RUC-NLPIR/WebThinker.

Prompt tuning in natural language processing (NLP) has become an increasingly popular method for adapting large language models to specific tasks. However, the transferability of these prompts, especially continuous prompts, between different models remains a challenge. In this work, we propose a zero-shot continuous prompt transfer method, where source prompts are encoded into relative space and the corresponding target prompts are searched for transferring to target models. Experimental results confirm the effectiveness of our method, showing that 'task semantics' in continuous prompts can be generalized across various language models. Moreover, we find that combining 'task semantics' from multiple source models can further enhance the performance of transfer.

Retrieval-Augmented Generation (RAG), by incorporating external knowledge with parametric memory of language models, has become the state-of-the-art architecture for opendomain QA tasks.However, common knowledge bases are inherently constrained by limited coverage and noisy information, making retrieval-based approaches inadequate to answer implicit reasoning questions.In this paper, we propose an Induction-Augmented Generation (IAG) framework that utilizes inductive knowledge along with the retrieved documents for implicit reasoning.We leverage large language models (LLMs) for deriving such knowledge via a novel prompting method based on inductive reasoning patterns.On top of this, we implement two versions of IAG named IAG-GPT and IAG-Student, respectively.IAG-GPT directly utilizes the knowledge generated by GPT-3 for answer prediction, while IAG-Student gets rid of dependencies on GPT service at inference time by incorporating a student inductor model.The inductor is firstly trained via knowledge distillation and further optimized by back-propagating the generator feedback via differentiable beam scores.Experimental results show that IAG outperforms RAG baselines as well as ChatGPT on two Open-Domain QA tasks.Notably, our best models have won the first place in the official leaderboards of CSQA2.0 (since Nov 1, 2022) and StrategyQA (since Jan 8, 2023).

Generalized text representations are the foundation of many natural language understanding tasks. To fully utilize the different corpus, it is inevitable that models need to understand the relevance among them. However, many methods ignore the relevance and adopt a single-channel model (a coarse paradigm) directly for all tasks, which lacks enough rationality and interpretation. In addition, some existing works learn downstream tasks by stitches skill block (a fine paradigm), which might cause irrational results due to its redundancy and noise. In this work, we first analyze the task correlation through three different perspectives, , data property, manual design, and model-based relevance, based on which the similar tasks are grouped together. Then, we propose a hierarchical framework with a coarse-to-fine paradigm, with the bottom level shared to all the tasks, the mid-level divided to different groups, and the top-level assigned to each of the tasks. This allows our model to learn basic language properties from all tasks, boost performance on relevant tasks, and reduce the negative impact from irrelevant tasks. Our experiments on 13 benchmark datasets across five natural language understanding tasks demonstrate the superiority of our method.

Immunofixation Electrophoresis (IFE) analysis is of great importance to the diagnosis of Multiple Myeloma, which is among the top-9 cancer killers in the United States, but has rarely been studied in the context of deep learning. Two possible reasons are: 1) the recognition of IFE patterns is dependent on the co-location of bands that forms a binary relation, different from the unary relation (visual features to label) that deep learning is good at modeling; 2) deep classification models may perform with high accuracy for IFE recognition but is not able to provide firm evidence (where the co-location patterns are) for its predictions, rendering difficulty for technicians to validate the results. We propose to address these issues with collocative learning, in which a collocative tensor has been constructed to transform the binary relations into unary relations that are compatible with conventional deep networks, and a location-label-free method that utilizes the Grad-CAM saliency map for evidence backtracking has been proposed for accurate localization. In addition, we have proposed Coached Attention Gates that can regulate the inference of the learning to be more consistent with human logic and thus support the evidence backtracking. The experimental results show that the proposed method has obtained a performance gain over its base model ResNet18 by 741.30% in IoU and also outperformed popular deep networks of DenseNet, CBAM, and Inception-v3.

As the applications on smartphones and tablets are getting richer and more powerful, people are more willing to do their daily works and entertainments on mobile devices. Sharing and collaborating on these devices in a convenient and safe way has become a growing demand in modern life. However, due to the lack of a flexible access control strategy of the official online services, typical applications such as email, video and music do not support this kind of sharing scheme. In this paper, we propose TrustyShare to provide a general sharing solution based on the ARM TrustZone technology which has a extremely wide range of applications in mobile terminal devices and Internet of Things devices. Our solution allows users to share services they enjoy without the official support from these services, while avoiding the disclosure of their private credentials. In addition, credential owners have full control on how and when others can use their services through flexible access control policies. We implement our solution on OP-TEE platform, and our experimental results demonstrate that TrustyShare works well with good performance.

WireGuard, a novel VPN proposed in 2017, has been widely accepted in the industry, since it is simpler, leaner and more efficient than traditional VPNs. However, WireGuard ignores the risks of key stolen and abused on both desktop and mobile platform. These vulnerabilities might be utilized by attackers to sneak into the protected network through VPN tunnel provided by WireGuard easily without permission. It is especially obvious on mobile platforms, since they are mostly online all day and the attack scenarios are more complicated and changeable. In this paper, we propose an enhanced WireGuard Android version called SeWG based on TEE. We use TEE (Trusted Execution Environment) technology to achieve secure key storage, preventing the misuse of the private key. And we design corresponding dynamic authentication mechanisms for user mode and kernel mode respectively, to prevent malware from sneaking into the secure tunnel. Finally, we implement SeWg scheme on QSEE, the TEE platform developed by Qualcomm. Our experimental results demonstrate that SeWG can work well with high efficiency.