Theory of Mind (ToM) is crucial for understanding social dialogue, where characters’ mental states are rarely stated explicitly but evolve through interaction and shape later behavior. Existing ToM benchmarks focus mainly on selected dialogue turns or state changes across separate scenarios, leaving within-dialogue mental state trajectories underexplored. We introduce TrajToM, a benchmark for evaluating whether LLMs can reason over evolving emotions, beliefs, intentions, and desires in continuous social dialogue. Built with a Sketch-first construction paradigm, TrajToM contains 700 dialogues and 18,165 multiple-choice questions across mental state reasoning, behavioral reasoning, and trajectory reasoning. Experiments reveal a substantial human-model gap, with GPT-5.2 reaching 67.4% overall accuracy compared with 88.2% for humans, and show persistent bottlenecks in second-order reasoning, behavior explanation, and change direction assessment. We further examine MARTA as an exploratory trajectory-aligned process-supervision framework, showing that explicit supervision over mental state trajectories can improve ToM reasoning.

Social media platforms provide an ideal environment to spread misinformation, where social bots can accelerate the spread. This paper explores the interplay between social bots and misinformation on the Sina Weibo platform. We construct a large-scale dataset that includes annotations for both misinformation and social bots. From the misinformation perspective, the dataset is multimodal, containing 11,393 pieces of misinformation and 16,416 pieces of verified information. From the social bot perspective, this dataset contains 65,749 social bots and 345,886 genuine accounts, annotated using a weakly supervised annotator. Extensive experiments demonstrate the comprehensiveness of the dataset, the clear distinction between misinformation and real information, and the high quality of social bot annotations. Further analysis illustrates that: (i) social bots are deeply involved in information spread; (ii) misinformation with the same topics has similar content, providing the basis of echo chambers, and social bots would amplify this phenomenon; and (iii) social bots generate similar content aiming to manipulate public opinions.

Evidence-enhanced detectors present remarkable abilities in identifying malicious social text. However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors. This paper explores potential manipulation scenarios including basic pollution, and rephrasing or generating evidence by LLMs. To mitigate the negative impact, we propose three defense strategies from the data and model sides, including machine-generated text detection, a mixture of experts, and parameter updating. Extensive experiments on four malicious social text detection tasks with ten datasets illustrate that evidence pollution significantly compromises detectors, where the generating strategy causes up to a 14.4% performance drop. Meanwhile, the defense strategies could mitigate evidence pollution, but they faced limitations for practical employment. Further analysis illustrates that polluted evidence (i) is of high quality, evaluated by metrics and humans; (ii) would compromise the model calibration, increasing expected calibration error up to 21.6%; and (iii) could be integrated to amplify the negative impact, especially for encoder-based LMs, where the accuracy drops by 21.8%.

Recently, question answering over temporal knowledge graphs (i.e., TKGQA) has been introduced and investigated, in quest of reasoning about dynamic factual knowledge. To foster research on TKGQA, a few datasets have been curated (e.g., CronQuestions and Complex-CronQuestions), and various models have been proposed based on these datasets. Nevertheless, existing efforts overlook the fact that real-life applications of TKGQA also tend to be complex in temporal granularity, i.e., the questions may concern mixed temporal granularities (e.g., both day and month). To overcome the limitation, in this paper, we motivate the notion of multi-granularity temporal question answering over knowledge graphs and present a large scale dataset for multi-granularity TKGQA, namely MultiTQ. To the best of our knowledge, MultiTQis among the first of its kind, and compared with existing datasets on TKGQA, MultiTQfeatures at least two desirable aspects—ample relevant facts and multiple temporal granularities. It is expected to better reflect real-world challenges, and serve as a test bed for TKGQA models. In addition, we propose a competing baseline MultiQA over MultiTQ, which is experimentally demonstrated to be effective in dealing with TKGQA. The data and code are released at https://github.com/czy1999/MultiTQ.

Nested named entity recognition (NER) is a task in which named entities may overlap with each other. Span-based approaches regard nested NER as a two-stage span enumeration and classification task, thus having the innate ability to handle this task. However, they face the problems of error propagation, ignorance of span boundary, difficulty in long entity recognition and requirement on large-scale annotated data. In this paper, we propose Extract-Select, a span selection framework for nested NER, to tackle these problems. Firstly, we introduce a span selection framework in which nested entities with different input categories would be separately extracted by the extractor, thus naturally avoiding error propagation in two-stage span-based approaches. In the inference phase, the trained extractor selects final results specific to the given entity category. Secondly, we propose a hybrid selection strategy in the extractor, which not only makes full use of span boundary but also improves the ability of long entity recognition. Thirdly, we design a discriminator to evaluate the extraction result, and train both extractor and discriminator with generative adversarial training (GAT). The use of GAT greatly alleviates the stress on the dataset size. Experimental results on four benchmark datasets demonstrate that Extract-Select outperforms competitive nested NER models, obtaining state-of-the-art results. The proposed model also performs well when less labeled data are given, proving the effectiveness of GAT.