Wikipedia serves as the world's largest and most popular online reference encyclopedia, rich in structured knowledge and authoritative citations. Recently, numerous works have leveraged large language models to automatically generate Wikipedia-like articles. However, existing approaches primarily focus on producing singular narrative-type content, overlooking higher information-density structured elements such as timeline and table. To address these limitations, we propose WikiMAG, a multi-agent guided framework for generating structured Wikipedia-like articles. This framework employs a collaborative multi-agent mechanism to orchestrate the creation process, featuring three synergistic core components: Progressive planner first constructs the coarse-grained outline framework and then annotate fine-grained types for outline units, encompassing narrative, timeline, and table formats; Reflective inspector dynamically curates high-quality references via multi-round interactive feedback, thereby enhancing the authority and relevance of citations; Versatile writer integrates fine-grained outline details and high-quality reference information to generate information-rich articles, incorporating the three annotated formats. We evaluate WikiMAG on two public datasets, FreshWiki and WikiGenBen, across outline, writing, and verifiability dimensions. Compared with the best baseline method, our method achieves an average improvement of 6.73 points and 4.39 points in Heading Soft Recall and the METEOR metric (a machine translation and text generation evaluation metric) respectively, and an average increase of 16.84 percentage points in Citation Rate.

Long-form books are among the most information-rich and structurally complex forms of written content, often exceeding 100,000 words. While recent methods have enabled basic long-text generation, they remain limited in two key aspects: the inability to generate ultra-long content at book scale, and the lack of mechanisms for integrating rich factual information. To address these limitations, we propose DeepWriter, a multi-agent collaborative framework that follows a structured planning-then-generation paradigm. It first constructs a detailed book outline with narrative arcs and chapter semantics, then incrementally generates content conditioned on retrieved knowledge and contextual signals. DeepWriter supports controllable generation of full-length books exceeding 100,000 words, enriched with citations, trivia and images. To support evaluation beyond surface-level fluency, we introduce DeepWriter-Bench, a bilingual benchmark of 18 annotated books designed to assess book-scale coherence, richness, and factual grounding. Additionally, we propose BookScore, a unified 100-point metric for quantifying book maturity. Experimental results show that DeepWriter achieves a state-of-the-art BookScore of 80.92, consistently outperforming strong baselines.

Large Reasoning Models (LRMs) achieve promising results on complex reasoning tasks but remain susceptible to hallucinations. Existing hallucination detection methods based on Large Language Models (LLMs) often focus solely on final answers, overlooking inconsistencies between the answer and reasoning process. This limitation reduces their ability to detect hallucinations during inference. Moreover, training-free approaches lack mechanisms for confidence estimation, resulting in an unquantified detection output. In contrast, training-based methods can provide fine-grained assessments but often neglect the self-correction capability of LRMs, where earlier errors may be corrected in subsequent steps, leading to inaccurate hallucination detection. To address these challenges, we propose ConfFuse, a unified framework that fuses global and local confidence scores for hallucination detection. A Global Hallucination Detection Model (GHDM) is trained using Direct Preference Optimization (DPO) to assess hallucinations at the level of entire reasoning chains, yielding global confidence estimates. Simultaneously, a Process Reward Model (PRM) estimates step-wise confidence scores to capture local logical flaws. A weighted fusion strategy combines the global confidence score with the minimum local score to jointly reflect overall reasoning consistency and local soundness. Experimental evaluations demonstrate that ConfFuse surpasses Qwen3-1.7B and Qwen3-8B by up to 11.86% and 5.46% in F1 score on in-distribution datasets, and achieves average improvements of 4.65% and 2.80% on out-of-distribution datasets. These results verify the effectiveness and generalizability of the proposed framework.

Zechen Sun, Yuyang Sun, Zecheng Tang, Juntao Li, Wenpeng Hu, Wenliang Chen, Zhunchen Luo, Guotong Geng, Min Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large Language Models (LLMs) have been widely applied in various domains such as education and healthcare, making safety assurance crucial.Jailbreak attacks, a method used in red-teaming, can help evaluate and improve the defensive strategies of LLMs.However, existing jailbreak methods often overlook the semantic differences across categories of harmful questions, leading to inconsistent success rates and reduced overall attack effectiveness.We propose the first category-aware jailbreak framework, SHARP, which incorporates the semantic category of harmful questions into prompt generation.Trained on a verified jailbreak dataset, SHARP enables the model to learn category-specific semantic features and adaptively generate prompts that bypass safety mechanisms.The method combines two-stage LoRA fine-tuning, and DPO-based reinforcement learning to optimize both attack success and category alignment.Experiments show that SHARP significantly improves attack success rates and achieves better cross-category robustness compared to the state-of-the-art (SOTA) baselines, providing an efficient and scalable tool for evaluating LLM safety.

Bo Zhang, Jiawei Zhang, Cong Gao, Bingxu Han, Minghao Hu, Jun Zhang, Yunbo Cao, Zhunchen Luo, Wen Yao, Guotong Geng, Zhong Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Various research has addressed the overconfidence problem, and we focus on improving the robustness of post-hoc calibration (e.g., temperature scaling, TS) when the test set shifts from the training set by image corruption. TS is greatly affected by the validation set, which previous work has proposed to perturb by Gaussian noise to improve calibration under domain drift. Inspired by this, we discovered that the same or similar augmentation on the validation set substantially improved TS under corrupted shift. We proposed a learnable and dynamic augmentation-based TS method, AugTS, which minimizes the maximum mean discrepancy (MMD) between the augmented validation and corrupted test set. Experiments on corrupted versions of CIFAR-10, CIFAR-100, and TinyImageNet show that AugTS can significantly improve calibration under corrupted shifts compared with competitive baselines.

Large language models (LLMs) are now pivotal in real-world applications. Model editing has emerged as a promising paradigm for efficiently modifying LLMs without full retraining. However, current editing approaches face significant limitations due to parameter drift, which stems from inconsistencies between newly edited knowledge and the model's existing knowledge. In sequential editing scenarios, cumulative drifts progressively lead to model collapse characterized by general capability degradation and balance between acquiring new knowledge and catastrophic forgetting of existing knowledge. Drawing inspiration from the hippocampal trisynaptic circuit for continual memorizing and forgetting, we propose a Hippocampal-like Sequential Editing (HSE) framework that designs the unlearning of obsolete knowledge, domain-specific knowledge update separation and replay for edited knowledge. Specifically, the HSE framework designs three core mechanisms: (1) Machine unlearning selectively erases outdated knowledge to facilitate integration of new information, (2) Fisher Information Matrix-guided parameter updates prevents cross-domain knowledge interference, and (3) Parameter replay consolidates long-term editing memory through lightweight and global replay of editing data in a parametric form. Theoretical analysis demonstrates that HSE achieves smaller generalization error bounds, more stable convergence and higher computational efficiency. Experimental results validate its effective balance between acquiring new knowledge and mitigating catastrophic forgetting, maintaining or even slightly enhancing general capabilities. In practical applications, experiments confirm its effectiveness in multi-domain hallucination mitigation, healthcare knowledge injecting, and societal bias reduction.

CLIP-guided zero-shot image generative model adaption methods only require textual domain labels without any target domain images, but there are some dilemmas remain unsolved, such as identity degradation and pattern overfitting. To address these issues, an adaptive domain-invariant feature transfer (ADIFT) method is proposed. It makes the target domain generator learn domain-invariant features from the source domain generator but learn domain-variant features from the CLIP space. We first introduce a local self-similarity map to represent and preserve the image identity features, and then add a parameter learnable point-wise gate module on the alignment path of the local self-similarity maps to transfer cross-domain features adaptively. Qualitative and quantitative experimental results validate that the proposed ADIFT solves the problems of identity degradation and pattern over-fitting effectively.