arXiv subjects

Ningnan Wang

Publications and source records attributed to Ningnan Wang.

9 recordsLinked to original sources

arXiv2026

The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation

Multi-agent LLM systems often treat consensus as evidence of successful interaction. For deliberative problems, however, reliability depends on whether agents preserve the facts and viewpoints needed to interpret an issue. We identify the deliberative illusion: discussion produces (1) factual attrition, the progressive loss of issue-critical facts, alongside (2) stance homogenization, the collapse of diverse positions toward consensus. To measure this process, we introduce DelibTrace, a framework that decomposes each issue into atomic facts, labels issue-critical ones, distributes them across agents, and tracks their survival across discussion rounds. Across ethical and news-based deliberation with three representative LLM families, multi-agent discussion erases up to 72% of issue-critical facts. This loss is consequential: retained evidence can reconstruct the issue misleadingly, final stances remain anchored in base-model priors, and a single malicious agent can inject misinformation into the shrinking shared context. These results reveal a sharper risk: agents can agree more while knowing less. We call for evaluations that measure which facts, uncertainties, and legitimate disagreements survive interaction.

cs.CL↗

arXiv2025

Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigation

Embodied visual navigation remains a challenging task, as agents must explore unknown environments with limited knowledge. Existing zero-shot studies have shown that incorporating memory mechanisms to support goal-directed behavior can improve long-horizon planning performance. However, they overlook visual frontier boundaries, which fundamentally dictate future trajectories and observations, and fall short of inferring the relationship between partial visual observations and navigation goals. In this paper, we propose Semantic Cognition Over Potential-based Exploration (SCOPE), a zero-shot framework that explicitly leverages frontier information to drive potential-based exploration, enabling more informed and goal-relevant decisions. SCOPE estimates exploration potential with a Vision-Language Model and organizes it into a spatio-temporal potential graph, capturing boundary dynamics to support long-horizon planning. In addition, SCOPE incorporates a self-reconsideration mechanism that revisits and refines prior decisions, enhancing reliability and reducing overconfident errors. Experimental results on two diverse embodied navigation tasks show that SCOPE outperforms state-of-the-art baselines by 4.6\% in accuracy. Further analysis demonstrates that its core components lead to improved calibration, stronger generalization, and higher decision quality.

cs.RO↗

arXiv2025

GuessBench: Sensemaking Multimodal Creativity in the Wild

We propose GuessBench, a novel benchmark that evaluates Vision Language Models (VLMs) on modeling the pervasive, noisy, and pluralistic human creativity. GuessBench sources data from "Guess the Build", an online multiplayer Minecraft minigame where one player constructs a Minecraft build given a concept (e.g. caterpillar) and others try to guess it with natural language hints, presenting a pristine testbed for sensemaking creativity in the wild with VLMs acting as guessers. We curate 1500 images from the actual gameplay and design 2000 problems spanning static and dynamic image settings, natural language hints of varying completeness, and more. Extensive experiments with six open/API VLMs and five reasoning enhancement approaches demonstrate that GuessBench presents a uniquely challenging task in creativity modeling: even the start-of-the-art GPT-4o is incorrect on 34% of instances, while we observe a huge performance gap (13.87% vs. 53.93% on average) between open and API models. When used as a resource to improve VLMs, fine-tuning on the reasoning traces for GuessBench problems improves visual perception tasks by 15.36% on average. Further analysis reveals that VLM performance in creativity sensemaking correlates with the frequency of the concept in training data, while the accuracy drops sharply for concepts in underrepresented cultural contexts and low-resource languages.

cs.CL↗

arXiv2024

What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection

Social media bot detection has always been an arms race between advancements in machine learning bot detectors and adversarial bot strategies to evade detection. In this work, we bring the arms race to the next level by investigating the opportunities and risks of state-of-the-art large language models (LLMs) in social bot detection. To investigate the opportunities, we design novel LLM-based bot detectors by proposing a mixture-of-heterogeneous-experts framework to divide and conquer diverse user information modalities. To illuminate the risks, we explore the possibility of LLM-guided manipulation of user textual and structured information to evade detection. Extensive experiments with three LLMs on two datasets demonstrate that instruction tuning on merely 1,000 annotated examples produces specialized LLMs that outperform state-of-the-art baselines by up to 9.1% on both datasets, while LLM-guided manipulation strategies could significantly bring down the performance of existing bot detectors by up to 29.6% and harm the calibration and reliability of bot detection systems.

cs.CL↗

arXiv2023

TwiBot-22: Towards Graph-Based Twitter Bot Detection

Twitter bot detection has become an increasingly important task to combat misinformation, facilitate social media moderation, and preserve the integrity of the online discourse. State-of-the-art bot detection methods generally leverage the graph structure of the Twitter network, and they exhibit promising performance when confronting novel Twitter bots that traditional methods fail to detect. However, very few of the existing Twitter bot detection datasets are graph-based, and even these few graph-based datasets suffer from limited dataset scale, incomplete graph structure, as well as low annotation quality. In fact, the lack of a large-scale graph-based Twitter bot detection benchmark that addresses these issues has seriously hindered the development and evaluation of novel graph-based bot detection approaches. In this paper, we propose TwiBot-22, a comprehensive graph-based Twitter bot detection benchmark that presents the largest dataset to date, provides diversified entities and relations on the Twitter network, and has considerably better annotation quality than existing datasets. In addition, we re-implement 35 representative Twitter bot detection baselines and evaluate them on 9 datasets, including TwiBot-22, to promote a fair comparison of model performance and a holistic understanding of research progress. To facilitate further research, we consolidate all implemented codes and datasets into the TwiBot-22 evaluation framework, where researchers could consistently evaluate new models and datasets. The TwiBot-22 Twitter bot detection benchmark and evaluation framework are publicly available at https://twibot22.github.io/

cs.SI↗

arXiv2022

PAR: Political Actor Representation Learning with Social Context and Expert Knowledge

Modeling the ideological perspectives of political actors is an essential task in computational political science with applications in many downstream tasks. Existing approaches are generally limited to textual data and voting records, while they neglect the rich social context and valuable expert knowledge for holistic ideological analysis. In this paper, we propose \textbf{PAR}, a \textbf{P}olitical \textbf{A}ctor \textbf{R}epresentation learning framework that jointly leverages social context and expert knowledge. Specifically, we retrieve and extract factual statements about legislators to leverage social context information. We then construct a heterogeneous information network to incorporate social context and use relational graph neural networks to learn legislator representations. Finally, we train PAR with three objectives to align representation learning with expert knowledge, model ideological stance consistency, and simulate the echo chamber phenomenon. Extensive experiments demonstrate that PAR is better at augmenting political text understanding and successfully advances the state-of-the-art in political perspective detection and roll call vote prediction. Further analysis proves that PAR learns representations that reflect the political reality and provide new insights into political behavior.

cs.CL↗

arXiv2021

BotRGCN: Twitter Bot Detection with Relational Graph Convolutional Networks

Twitter bot detection is an important and challenging task. Existing bot detection measures fail to address the challenge of community and disguise, falling short of detecting bots that disguise as genuine users and attack collectively. To address these two challenges of Twitter bot detection, we propose BotRGCN, which is short for Bot detection with Relational Graph Convolutional Networks. BotRGCN addresses the challenge of community by constructing a heterogeneous graph from follow relationships and applies relational graph convolutional networks. Apart from that, BotRGCN makes use of multi-modal user semantic and property information to avoid feature engineering and augment its ability to capture bots with diversified disguise. Extensive experiments demonstrate that BotRGCN outperforms competitive baselines on a comprehensive benchmark TwiBot-20 which provides follow relationships.

cs.SI↗

arXiv2021

SATAR: A Self-supervised Approach to Twitter Account Representation Learning and its Application in Bot Detection

Twitter has become a major social media platform since its launching in 2006, while complaints about bot accounts have increased recently. Although extensive research efforts have been made, the state-of-the-art bot detection methods fall short of generalizability and adaptability. Specifically, previous bot detectors leverage only a small fraction of user information and are often trained on datasets that only cover few types of bots. As a result, they fail to generalize to real-world scenarios on the Twittersphere where different types of bots co-exist. Additionally, bots in Twitter are constantly evolving to evade detection. Previous efforts, although effective once in their context, fail to adapt to new generations of Twitter bots. To address the two challenges of Twitter bot detection, we propose SATAR, a self-supervised representation learning framework of Twitter users, and apply it to the task of bot detection. In particular, SATAR generalizes by jointly leveraging the semantics, property and neighborhood information of a specific user. Meanwhile, SATAR adapts by pre-training on a massive number of self-supervised users and fine-tuning on detailed bot detection scenarios. Extensive experiments demonstrate that SATAR outperforms competitive baselines on different bot detection datasets of varying information completeness and collection time. SATAR is also proved to generalize in real-world scenarios and adapt to evolving generations of social media bots.

cs.SI↗

arXiv2021

TwiBot-20: A Comprehensive Twitter Bot Detection Benchmark

Twitter has become a vital social media platform while an ample amount of malicious Twitter bots exist and induce undesirable social effects. Successful Twitter bot detection proposals are generally supervised, which rely heavily on large-scale datasets. However, existing benchmarks generally suffer from low levels of user diversity, limited user information and data scarcity. Therefore, these datasets are not sufficient to train and stably benchmark bot detection measures. To alleviate these problems, we present TwiBot-20, a massive Twitter bot detection benchmark, which contains 229,573 users, 33,488,192 tweets, 8,723,736 user property items and 455,958 follow relationships. TwiBot-20 covers diversified bots and genuine users to better represent the real-world Twittersphere. TwiBot-20 also includes three modals of user information to support both binary classification of single users and community-aware approaches. To the best of our knowledge, TwiBot-20 is the largest Twitter bot detection benchmark to date. We reproduce competitive bot detection methods and conduct a thorough evaluation on TwiBot-20 and two other public datasets. Experiment results demonstrate that existing bot detection measures fail to match their previously claimed performance on TwiBot-20, which suggests that Twitter bot detection remains a challenging task and requires further research efforts.

cs.SI↗