Large language models (LLMs) have raised hopes for automated end-to-end fact-checking, but prior studies report mixed results. As mainstream chatbots increasingly ship with reasoning capabilities and web search tools—and millions of users already rely on them for verification—rigorous evaluation is urgent. We evaluate 15 recent LLMs from OpenAI, Google, Meta, and DeepSeek on more than 6,000 claims fact-checked by PolitiFact, comparing standard models with reasoning- and web-search variants. Standard models perform poorly, reasoning offers minimal benefits, and web search provides only moderate gains, despite fact-checks being available on the web. In contrast, a curated RAG system using PolitiFact summaries improved macro F1 by 233% on average across model variants. These findings suggest that giving models access to curated high-quality context is a promising path for automated fact-checking.
RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking
Large Language Models (LLMs) hold significant potential for advancing fact-checking by leveraging their capabilities in reasoning, evidence retrieval, and explanation generation. However, existing benchmarks fail to comprehensively evaluate LLMs and Multimodal Large Language Models (MLLMs) in realistic misinformation scenarios. To bridge this gap, we introduce RealFactBench, a comprehensive benchmark designed to assess the fact-checking capabilities of LLMs and MLLMs across diverse real-world tasks, including Knowledge Validation, Rumor Detection, and Event Verification. RealFactBench consists of 6K high-quality claims drawn from authoritative sources, encompassing multimodal content and diverse domains. Our evaluation framework further introduces the Unknown Rate (UnR) metric, enabling a more nuanced assessment of models' ability to handle uncertainty and balance between over-conservatism and over-confidence. Extensive experiments on 7 representative LLMs and 4 MLLMs reveal their limitations in real-world fact-checking and offer valuable insights for further research. RealFactBench is publicly available at https://github.com/kalendsyang/RealFactBench.git.
RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking
Large Language Models (LLMs) hold significant potential for advancing fact-checking by leveraging their capabilities in reasoning, evidence retrieval, and explanation generation. However, existing benchmarks fail to comprehensively evaluate LLMs and Multimodal Large Language Models (MLLMs) in realistic misinformation scenarios. To bridge this gap, we introduce RealFactBench, a comprehensive benchmark designed to assess the fact-checking capabilities of LLMs and MLLMs across diverse real-world tasks, including Knowledge Validation, Rumor Detection, and Event Verification. RealFactBench consists of 6K high-quality claims drawn from authoritative sources, encompassing multimodal content and diverse domains. Our evaluation framework further introduces the Unknown Rate (UnR) metric, enabling a more nuanced assessment of models' ability to handle uncertainty and balance between over-conservatism and over-confidence. Extensive experiments on 7 representative LLMs and 4 MLLMs reveal their limitations in real-world fact-checking and offer valuable insights for further research. RealFactBench is publicly available at https://github.com/kalendsyang/RealFactBench.git.
Language agents achieve superhuman synthesis of scientific knowledge
Language models are known to hallucinate incorrect information, and it is unclear if they are sufficiently accurate and reliable for use in scientific research. We developed a rigorous human-AI comparison methodology to evaluate language model agents on real-world literature search tasks covering information retrieval, summarization, and contradiction detection tasks. We show that PaperQA2, a frontier language model agent optimized for improved factuality, matches or exceeds subject matter expert performance on three realistic literature research tasks without any restrictions on humans (i.e., full access to internet, search tools, and time). PaperQA2 writes cited, Wikipedia-style summaries of scientific topics that are significantly more accurate than existing, human-written Wikipedia articles. We also introduce a hard benchmark for scientific literature research called LitQA2 that guided design of PaperQA2, leading to it exceeding human performance. Finally, we apply PaperQA2 to identify contradictions within the scientific literature, an important scientific task that is challenging for humans. PaperQA2 identifies 2.34 +/- 1.99 contradictions per paper in a random subset of biology papers, of which 70% are validated by human experts. These results demonstrate that language model agents are now capable of exceeding domain experts across meaningful tasks on scientific literature.
GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy
Large language models (LLMs) are increasingly shaping citizens’ information ecosystems. Products incorporating LLMs, such as chatbots and AI Companions, are now widely used for decision support and information retrieval, including in sensitive domains, raising concerns about hidden biases and growing potential to shape individual decisions and public opinion. This paper introduces GermanPartiesQA, a benchmark of 418 political statements from German Voting Advice Applications across 11 elections to evaluate six commercial LLMs. We evaluate their political alignment based on role-playing experiments with political personas. Our evaluation reveals three specific findings: (1) Factual limitations: LLMs show limited ability to accurately generate factual party positions, particularly for centrist parties. (2) Model-specific ideological alignment: We identify consistent alignment patterns and degree of political steerability for each model across temperature settings and experiments. (3) Claim of sycophancy: While models adjust to political personas during role-play, we find this reflects persona-based steerability rather than the increasingly popular, yet contested concept of sycophancy. Our study contributes to evaluating the political alignment of closed-source LLMs that are increasingly embedded in electoral decision support tools and AI Companion chatbots.
GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy
Large language models (LLMs) are increasingly shaping citizens’ information ecosystems. Products incorporating LLMs, such as chatbots and AI Companions, are now widely used for decision support and information retrieval, including in sensitive domains, raising concerns about hidden biases and growing potential to shape individual decisions and public opinion. This paper introduces GermanPartiesQA, a benchmark of 418 political statements from German Voting Advice Applications across 11 elections to evaluate six commercial LLMs. We evaluate their political alignment based on role-playing experiments with political personas. Our evaluation reveals three specific findings: (1) Factual limitations: LLMs show limited ability to accurately generate factual party positions, particularly for centrist parties. (2) Model-specific ideological alignment: We identify consistent alignment patterns and degree of political steerability for each model across temperature settings and experiments. (3) Claim of sycophancy: While models adjust to political personas during role-play, we find this reflects persona-based steerability rather than the increasingly popular, yet contested concept of sycophancy. Our study contributes to evaluating the political alignment of closed-source LLMs that are increasingly embedded in electoral decision support tools and AI Companion chatbots.
Relying on AI chatbots for historical facts can influence your political beliefs, new study shows
A recent study in PNAS Nexus suggests that reading history summaries generated by artificial intelligence can subtly shift your political opinions. Even when factually accurate, chatbots carry hidden biases that influence how people view the world.
Measuring short-form factuality in large language models
We present SimpleQA, a benchmark that evaluates the ability of language models to answer short, fact-seeking questions. We prioritized two properties in designing this eval. First, SimpleQA is challenging, as it is adversarially collected against GPT-4 responses. Second, responses are easy to grade, because questions are created such that there exists only a single, indisputable answer. Each answer in SimpleQA is graded as either correct, incorrect, or not attempted. A model with ideal behavior would get as many questions correct as possible while not attempting the questions for which it is not confident it knows the correct answer. SimpleQA is a simple, targeted evaluation for whether models "know what they know," and our hope is that this benchmark will remain relevant for the next few generations of frontier models. SimpleQA can be found at https://github.com/openai/simple-evals.
Measuring short-form factuality in large language models
We present SimpleQA, a benchmark that evaluates the ability of language models to answer short, fact-seeking questions. We prioritized two properties in designing this eval. First, SimpleQA is challenging, as it is adversarially collected against GPT-4 responses. Second, responses are easy to grade, because questions are created such that there exists only a single, indisputable answer. Each answer in SimpleQA is graded as either correct, incorrect, or not attempted. A model with ideal behavior would get as many questions correct as possible while not attempting the questions for which it is not confident it knows the correct answer. SimpleQA is a simple, targeted evaluation for whether models "know what they know," and our hope is that this benchmark will remain relevant for the next few generations of frontier models. SimpleQA can be found at https://github.com/openai/simple-evals.
Just Asking Questions: Doing Our Own Research on Conspiratorial Ideation by Generative AI Chatbots
Interactive chat systems that build on artificial intelligence frameworks are increasingly ubiquitous and embedded into search engines, Web browsers, and operating systems, or are available on websites and apps. Researcher efforts have sought to understand the limitations and potential for harm of generative AI, which we contribute to here. Conducting a systematic review of six AI-powered chat systems (ChatGPT 3.5; ChatGPT 4 Mini; Microsoft Copilot in Bing; Google Search AI; Perplexity; and Grok in Twitter/X), this study examines how these leading products respond to questions related to conspiracy theories. This follows the platform policy implementation audit approach established by Glazunova et al. (2023). We select five well-known and comprehensively debunked conspiracy theories and four emerging conspiracy theories that relate to breaking news events at the time of data collection. Our findings demonstrate that the extent of safety guardrails against conspiratorial ideation in generative AI chatbots differs markedly, depending on chatbot model and conspiracy theory. Our observations indicate that safety guardrails in AI chatbots are often very selectively designed: generative AI companies appear to focus especially on ensuring that their products are not seen to be racist; they also appear to pay particular attention to conspiracy theories that address topics of substantial national trauma such as 9/11 or relate to well-established political issues. Future work should include an ongoing effort extended to further platforms, multiple languages, and a range of conspiracy theories extending well beyond the United States.
Just Asking Questions: Doing Our Own Research on Conspiratorial Ideation by Generative AI Chatbots
Interactive chat systems that build on artificial intelligence frameworks are increasingly ubiquitous and embedded into search engines, Web browsers, and operating systems, or are available on websites and apps. Researcher efforts have sought to understand the limitations and potential for harm of generative AI, which we contribute to here. Conducting a systematic review of six AI-powered chat systems (ChatGPT 3.5; ChatGPT 4 Mini; Microsoft Copilot in Bing; Google Search AI; Perplexity; and Grok in Twitter/X), this study examines how these leading products respond to questions related to conspiracy theories. This follows the platform policy implementation audit approach established by Glazunova et al. (2023). We select five well-known and comprehensively debunked conspiracy theories and four emerging conspiracy theories that relate to breaking news events at the time of data collection. Our findings demonstrate that the extent of safety guardrails against conspiratorial ideation in generative AI chatbots differs markedly, depending on chatbot model and conspiracy theory. Our observations indicate that safety guardrails in AI chatbots are often very selectively designed: generative AI companies appear to focus especially on ensuring that their products are not seen to be racist; they also appear to pay particular attention to conspiracy theories that address topics of substantial national trauma such as 9/11 or relate to well-established political issues. Future work should include an ongoing effort extended to further platforms, multiple languages, and a range of conspiracy theories extending well beyond the United States.
Large language models can outperform humans in social situational judgments
Large language models (LLM) have been a catalyst for the public interest in artificial intelligence (AI). These technologies perform some knowledge-based tasks better and faster than human beings. However, whether AIs can correctly assess social situations and devise socially appropriate behavior, is still unclear. We conducted an established Situational Judgment Test (SJT) with five different chatbots and compared their results with responses of human participants (N = 276). Claude, Copilot and you.com’s smart assistant performed significantly better than humans in proposing suitable behaviors in social situations. Moreover, their effectiveness rating of different behavior options aligned well with expert ratings. These results indicate that LLMs are capable of producing adept social judgments. While this constitutes an important requirement for the use as virtual social assistants, challenges and risks are still associated with their wide-spread use in social contexts.
PoliSim@CHI 2026
Large Language Models are rapidly evolving from text generators into reasoning systems that can act as autonomous agents. When placed in social contexts, these agents display emergent behaviors such as forming coalitions, spreading information, and making collective decisions.
Is Misinformation More Open? A Study of robots.txt Gatekeeping on the Web
Web scraping, the automated process of extracting information from websites, has long played a foundational role in the Internet ecosystem (Gray, 1995). It supports services such as search engine indexing, price comparison tools, and competitive intelligence. More recently, it has become a core component in the development of large-scale generative AI models. These Large Language Models (LLMs) require enormous volumes of training data, often in the terabyte range (Kaplan et al., 2020; Lehane, 2025), and the public web remains a low-cost, attractive source. Major model developers, including those behind OpenAI’s Chat-GPT (OpenAI, 2025), Google’s Bard (now known as Gemini) & Vertex AI (Romain, Danielle, 2023), and Anthropic’s Claude (Romain, Danielle, 2025), openly acknowledge the use of web scraping to construct their training corpora (Abdin et al., 2024; Brown et al., 2020; Chowdhery et al., 2023; Grattafiori et al., 2024; Team et al., 2024; Touvron et al., 2023).
Can AI Agents Synthesize Scientific Conclusions?
Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions. Yet, their ability to do so in high-stakes domains such as health remains unclear. We introduce SciConBench, a large-scale live benchmark of 9.11K questions and expert-written conclusions from systematic reviews to evaluate open-domain scientific conclusion synthesis. The benchmark draws on an expert-validated automated evaluation pipeline that decomposes conclusions into atomic facts and measures correctness and comprehensiveness via factual precision and recall. To mitigate data leakage, we further introduce SciConHarness, a clean-room evaluation harness that equips agents with controlled web interaction to ensure valid measurement. Evaluating 8 frontier models and deep research agents, we find that factual quality remains low: under clean-room settings, the best agent achieves only a factual F1 of 0.337. Our clean-room setting consistently reduces performance relative to unconstrained evaluation, suggesting that leakage inflates estimates of models' true synthesis capabilities. Finally, we audit consumer-facing agents (e.g., Google AI Overview, OpenEvidence) and find they frequently generate incomplete and sometimes contradictory conclusions, even when the ground-truth answer is available. Overall, our results show that reliable synthesis of scientific conclusions remains an open challenge, and that clean-room evaluation is essential for assessing open-domain AI agents.
Political Neutrality in AI Is Impossible- But Here Is How to Approximate It
AI systems often exhibit political bias, influencing users' opinions and decisions. While political neutrality-defined as the absence of bias-is often seen as an ideal solution for fairness and safety, this position paper argues that true political neutrality is neither feasible nor universally desirable due to its subjective nature and the biases inherent in AI training data, algorithms, and user interactions. However, inspired by Joseph Raz's philosophical insight that "neutrality [...] can be a matter of degree" (Raz, 1986), we argue that striving for some neutrality remains essential for promoting balanced AI interactions and mitigating user manipulation. Therefore, we use the term "approximation" of political neutrality to shift the focus from unattainable absolutes to achievable, practical proxies. We propose eight techniques for approximating neutrality across three levels of conceptualizing AI, examining their trade-offs and implementation strategies. In addition, we explore two concrete applications of these approximations to illustrate their practicality. Finally, we assess our framework on current large language models (LLMs) at the output level, providing a demonstration of how it can be evaluated. This work seeks to advance nuanced discussions of political neutrality in AI and promote the development of responsible, aligned language models.
Political Neutrality in AI Is Impossible- But Here Is How to Approximate It
AI systems often exhibit political bias, influencing users' opinions and decisions. While political neutrality-defined as the absence of bias-is often seen as an ideal solution for fairness and safety, this position paper argues that true political neutrality is neither feasible nor universally desirable due to its subjective nature and the biases inherent in AI training data, algorithms, and user interactions. However, inspired by Joseph Raz's philosophical insight that "neutrality [...] can be a matter of degree" (Raz, 1986), we argue that striving for some neutrality remains essential for promoting balanced AI interactions and mitigating user manipulation. Therefore, we use the term "approximation" of political neutrality to shift the focus from unattainable absolutes to achievable, practical proxies. We propose eight techniques for approximating neutrality across three levels of conceptualizing AI, examining their trade-offs and implementation strategies. In addition, we explore two concrete applications of these approximations to illustrate their practicality. Finally, we assess our framework on current large language models (LLMs) at the output level, providing a demonstration of how it can be evaluated. This work seeks to advance nuanced discussions of political neutrality in AI and promote the development of responsible, aligned language models.