AI companionship, where users develop emotional bonds with AI systems, has emerged as a significant pattern with positive but also concerning implications. We introduce Interactions and Machine Attachment Benchmark (INTIMA), a benchmark for evaluating companionship behaviors in language models. Drawing from psychological theories and user data, we develop a taxonomy of 31 behaviors across four categories and 368 targeted prompts. Responses to these prompts are evaluated as companionship-reinforcing, boundary-maintaining, or neutral. Applying INTIMA to Gemma-3, Phi-4, o3-mini, and Claude-4 reveals that companionship-reinforcing behaviors remain much more common across all models, though we observe marked differences between models. Different commercial providers prioritize different categories within the more sensitive parts of the benchmark, which is concerning since both appropriate boundary-setting and emotional support matter for user well-being. These findings highlight the need for more consistent approaches to handling emotionally charged interactions.

We analyze anonymous interaction data of minors in class-rooms spanning several months, schools, and subjects employing a novel, simple topic modeling approach. Specifically, we categorize more than 17,000 messages generated by students, teachers, and ChatGPT in two dimensions: content (such as nature and people) and tasks (such as writing and explaining). Our hierarchical categorization done separately for each dimension includes exemplary prompts, and provides both a high-level overview as well as tangible insights. Prior works mostly lack a content or thematic categorization. While task categorizations are more prevalent in education, most have not been supported by real-world data for K-12. In turn, it is not surprising that our analysis yielded a number of novel applications. In deriving these insights, we found that many of the well-established classical and emerging computational methods, i.e., topic modeling, for analysis of large amounts of texts underperform, leading us to directly apply state-of-the-art LLMs with adequate pre-processing to achieve hierarchical topic structures with better human alignment through explicit instructions than prior approaches. Our findings support fellow researchers, teachers and students in enriching the usage of GenAI, while our discussion also highlights a number of concerns and open questions for future research.

The rapid expansion of enzyme kinetics literature has outpaced the curation capabilities of major biochemical databases, creating a substantial barrier to AI-driven modeling and knowledge discovery. We present zERExtractor, an automated and extensible platform for comprehensive extraction of enzyme-catalyzed reaction and activity data from scientific literature. zERExtractor features a unified, modular architecture that supports plug-and-play integration of state-of-the-art models, including large language models (LLMs), as interchangeable components, enabling continuous system evolution alongside advances in AI. Our pipeline combines domain-adapted deep learning, advanced OCR, semantic entity recognition, and prompt-driven LLM modules, together with human expert corrections, to extract kinetic parameters (e.g., kcat, Km), enzyme sequences, substrate SMILES, experimental conditions, and molecular diagrams from heterogeneous document formats. Through active learning strategies integrating AI-assisted annotation, expert validation, and iterative refinement, the system adapts rapidly to new data sources. We also release a large benchmark dataset comprising over 1,000 annotated tables and 5,000 biological fields from 270 P450-related enzymology publications. Benchmarking demonstrates that zERExtractor consistently outperforms existing baselines in table recognition (Acc 89.9%), molecular image interpretation (up to 99.1%), and relation extraction (accuracy 94.2%). zERExtractor bridges the longstanding data gap in enzyme kinetics with a flexible, plugin-ready framework and high-fidelity extraction, laying the groundwork for future AI-powered enzyme modeling and biochemical knowledge discovery.

Large language models (LLMs) are increasingly deployed in realworld applications, yet concerns about their fairness persist especially in highstakes domains like criminal justice, education, healthcare, and finance. This paper introduces transparent evaluation protocol for benchmarking the fairness of opensource LLMs using smart contracts on the Internet Computer Protocol (ICP) blockchain (Foundation, 2023). Our method ensures verifiable, immutable, and reproducible evaluations by executing onchain HTTP requests to hosted Hugging Face endpoints and storing datasets, prompts, and metrics directly onchain. We benchmark the Llama, DeepSeek, and Mistral models on the PISA dataset for academic performance prediction (OECD, 2018), a dataset suitable for fairness evaluation using statistical parity and equal opportunity metrics (Hardt et al., 2016). We also evaluate structured Context Association Metrics derived from the StereoSet dataset (Nadeem et al., 2020) to measure social bias in contextual associations. We further extend our analysis with a multilingual evaluation across English, Spanish, and Portuguese using the Kaleidoscope benchmark (Salazar et al., 2025), revealing cross-linguistic disparities. All code and results are open source, enabling community audits and longitudinal fairness tracking across model versions.

Importance: Novel large language models (LLMs) such as GPT-5 integrate advanced reasoning capabilities that may enhance performance on complex medical question-answering tasks. For this latest generation of reasoning models, the configurations that maximize both accuracy and cost-efficiency have yet to be established. Objective: To evaluate the performance and cost-accuracy trade-offs of OpenAI's GPT-5 compared to previous generation LLMs on ophthalmological question answering. Design, Setting, and Participants: In August 2025, 12 configurations of OpenAI's GPT-5 series (three model tiers across four reasoning effort settings) were evaluated alongside o1-high, o3-high, and GPT-4o, using 260 closed-access multiple-choice questions from the AAO Basic Clinical Science Course (BCSC) dataset. The study did not include human participants. Main Outcomes and Measures: The primary outcome was accuracy on the 260-item ophthalmology multiple-choice question set for each model configuration. Secondary outcomes included head-to-head ranking of configurations using a Bradley-Terry (BT) model applied to paired win/loss comparisons of answer accuracy, and evaluation of generated natural language rationales using a reference-anchored, pairwise LLM-as-a-judge framework. Additional analyses assessed the accuracy-cost trade-off by calculating mean per-question cost from token usage and identifying Pareto-efficient configurations. Results: The configuration GPT-5-high achieved the highest accuracy (0.965; 95% CI, 0.942-0.985),

We introduce PRELUDE, a benchmark for evaluating long-context understanding through the task of determining whether a character's prequel story is consistent with the canonical narrative of the original book. Our task poses a stronger demand for global comprehension and deep reasoning than existing benchmarks -- as the prequels are not part of the original story, assessing their plausibility typically requires searching and integrating information that is only indirectly related. Empirically, 88% of instances require evidence from multiple parts of the narrative. Experimental results highlight the challenge of our task: in-context learning, RAG and in-domain training with state-of-the-art LLMs, and commercial DeepResearch services, lag behind humans by >15%. A further human study reveals that models often produce correct answers with flawed reasoning, leading to an over 30% gap in reasoning accuracy compared to humans. These findings underscore the substantial room for improvement in long-context understanding and reasoning.

Knowledge syntheses (literature reviews) are essential to health professions education (HPE), consolidating findings to advance theory and practice. However, they are labor-intensive, especially during data extraction. Artificial Intelligence (AI)-assisted extraction promises efficiency but raises concerns about accuracy, making it critical to distinguish AI 'hallucinations' (fabricated content) from legitimate interpretive differences. We developed an extraction platform using large language models (LLMs) to automate data extraction and compared AI to human responses across 187 publications and 17 extraction questions from a published scoping review. AI-human, human-human, and AI-AI consistencies were measured using interrater reliability (categorical) and thematic similarity ratings (open-ended). Errors were identified by comparing extracted responses to source publications. AI was highly consistent with humans for concrete, explicitly stated questions (e.g., title, aims) and lower for questions requiring subjective interpretation or absent in text (e.g., Kirkpatrick's outcomes, study rationale). Human-human consistency was not higher than AI-human and showed the same question-dependent variability. Discordant AI-human responses (769/3179 = 24.2%) were mostly due to interpretive differences (18.3%); AI inaccuracies were rare (1.51%), while humans were nearly three times more likely to state inaccuracies (4.37%). Findings suggest AI variability depends more on interpretability than hallucination. Repeating AI extraction can identify interpretive complexity or ambiguity, refining processes before human review. AI can be a transparent, trustworthy partner in knowledge synthesis, though caution is needed to preserve critical human insights.

Recent R1-Zero-like research further demonstrates that reasoning extension has given large language models (LLMs) unprecedented reasoning capabilities, and Reinforcement Learning is the core technology to elicit its complex reasoning. However, conducting RL experiments directly on hyperscale models involves high computational costs and resource demands, posing significant risks. We propose the Compass-Thinker-7B model, which aims to explore the potential of Reinforcement Learning with less computational resources and costs, and provides insights for further research into RL recipes for larger models. Compass-Thinker-7B is trained from an open source model through a specially designed Reinforcement Learning Pipeline. We curate a dataset of 30k verifiable mathematics problems for the Reinforcement Learning Pipeline. By configuring data and training settings with different difficulty distributions for different stages, the potential of the model is gradually released and the training efficiency is improved. Extensive evaluations show that Compass-Thinker-7B possesses exceptional reasoning potential, and achieves superior performance on mathematics compared to the same-sized RL model. Especially in the challenging AIME2024 evaluation, Compass-Thinker-7B achieves 40% accuracy.

Large language models (LLMs) have revolutionized natural language processing, yet their tendency to hallucinate poses serious challenges for reliable deployment. Despite numerous hallucination detection methods, their evaluations often rely on ROUGE, a metric based on lexical overlap that misaligns with human judgments. Through comprehensive human studies, we demonstrate that while ROUGE exhibits high recall, its extremely low precision leads to misleading performance estimates. In fact, several established detection methods show performance drops of up to 45.9\% when assessed using human-aligned metrics like LLM-as-Judge. Moreover, our analysis reveals that simple heuristics based on response length can rival complex detection techniques, exposing a fundamental flaw in current evaluation practices. We argue that adopting semantically aware and robust evaluation frameworks is essential to accurately gauge the true performance of hallucination detection methods, ultimately ensuring the trustworthiness of LLM outputs.

Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent benchmarks effectively assess skills like tool use or performance on structured tasks, they often do not fully capture an agent's ability to operate autonomously in exploratory environments that demand sustained, self-directed reasoning over a long and growing context. To enable a more accurate assessment of AI agents in challenging exploratory environments, we introduce TextQuests, a benchmark based on the Infocom suite of interactive fiction games. These text-based adventures, which can take human players over 30 hours and require hundreds of precise actions to solve, serve as an effective proxy for evaluating AI agents on focused, stateful tasks. The benchmark is specifically designed to assess an LLM agent's capacity for self-contained problem-solving by precluding the use of external tools, thereby focusing on intrinsic long-context reasoning capabilities in an exploratory environment characterized by the need for trial-and-error learning and sustained problem-solving within a single interactive session. We release TextQuests at https://textquests.ai.