Today, large language models are widely used as judges to evaluate responses from other language models. Hence, it is imperative to benchmark and improve these LLM-judges on real-world language model usage: a typical human-assistant conversation is lengthy, and shows significant diversity in topics, intents, and requirements across turns, e.g. social interactions, task requests, feedback. We present Amulet, a framework that leverages pertinent linguistic concepts of dialog-acts and maxims to improve the accuracy of LLM-judges on preference data with complex, multi-turn conversational context. Amulet presents valuable insights about (a) the communicative structures and intents present in the conversation (dialog acts), and (b) the satisfaction of conversational principles (maxims) by the preference responses, and uses them to make judgments. On four challenging datasets, Amulet shows that (a) humans frequently (60 to 70 percent of the time) change their intents from one turn of the conversation to the next, and (b) in 75 percent of instances, the preference responses can be differentiated via dialog acts and/or maxims, reiterating the latter's significance in judging such data. Amulet can be used either as a judge by applying the framework to a single LLM, or integrated into a jury with different LLM judges; our judges and juries show strong improvements on relevant baselines for all four datasets.

We investigate the existence and persistence of a specific type of gender bias in some of the popular LLMs and contribute a new benchmark dataset, RealWorldQuestioning (released on HuggingFace ), developed from real-world questions across four key domains in business and health contexts: education, jobs, personal financial management, and general health. We define and study entropy bias, which we define as a discrepancy in the amount of information generated by an LLM in response to real questions users have asked. We tested this using four different LLMs and evaluated the generated responses both qualitatively and quantitatively by using ChatGPT-4o (as "LLM-as-judge"). Our analyses (metric-based comparisons and "LLM-as-judge" evaluation) suggest that there is no significant bias in LLM responses for men and women at a category level. However, at a finer granularity (the individual question level), there are substantial differences in LLM responses for men and women in the majority of cases, which "cancel" each other out often due to some responses being better for males and vice versa. This is still a concern since typical users of these tools often ask a specific question (only) as opposed to several varied ones in each of these common yet important areas of life. We suggest a simple debiasing approach that iteratively merges the responses for the two genders to produce a final result. Our approach demonstrates that a simple, prompt-based debiasing strategy can effectively debias LLM outputs, thus producing responses with higher information content than both gendered variants in 78% of the cases, and consistently achieving a balanced integration in the remaining cases.

According to the World Health Organization (WHO), over 2.3 million women were diagnosed with breast cancer in 2020, making it the most diagnosed cancer worldwide and the leading cause of cancer-related deaths among women (WHO, 2021). The incidence of breast cancer is rising by around 3% per year, with higher mortality rates observed in lower-income countries due to limited access to early screening and treatment. In wealthier nations, 1 in 12 women are diagnosed with breast cancer, whereas in lower-income countries, the rate is 1 in 27. More concerning is the disparity in mortality--1 in 48 women die from breast cancer in low-income countries compared to 1 in 71 in high-income countries (WHO, 2022). In sub-Saharan Africa, breast cancer now has the highest mortality rate among all cancers affecting women, surpassing cervical cancer.

As protein informatics advances rapidly, the demand for enhanced predictive accuracy, structural analysis, and functional understanding has intensified. Transformer models, as powerful deep learning architectures, have demonstrated unprecedented potential in addressing diverse challenges across protein research. However, a comprehensive review of Transformer applications in this field remains lacking. This paper bridges this gap by surveying over 100 studies, offering an in-depth analysis of practical implementations and research progress of Transformers in protein-related tasks. Our review systematically covers critical domains, including protein structure prediction, function prediction, protein-protein interaction analysis, functional annotation, and drug discovery/target identification. To contextualize these advancements across various protein domains, we adopt a domain-oriented classification system. We first introduce foundational concepts: the Transformer architecture and attention mechanisms, categorize Transformer variants tailored for protein science, and summarize essential protein knowledge. For each research domain, we outline its objectives and background, critically evaluate prior methods and their limitations, and highlight transformative contributions enabled by Transformer models. We also curate and summarize pivotal datasets and open-source code resources to facilitate reproducibility and benchmarking. Finally, we discuss persistent challenges in applying Transformers to protein informatics and propose future research directions. This review aims to provide a consolidated foundation for the synergistic integration of Transformer and protein informatics, fostering further innovation and expanded applications in the field.

Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal, multi-device meeting transcription by incorporating video modality alongside audio. The tasks include Audio-Visual Speaker Di-arization (A VSD), Audio-Visual Speech Recognition (A VSR), and Audio-Visual Diarization and Recognition (A VDR). We present the challenge's objectives, tasks, dataset, baseline systems, and solutions proposed by participants. The best-performing systems achieved significant improvements over the baseline: the top A VSD model achieved a Diarization Error Rate (DER) of 8.09%, improving by 7.43%; the top A VSR system achieved a Character Error Rate (CER) of 9.48%, improving by 10.62%; and the best A VDR system achieved a concatenated minimum-permutation Character Error Rate (cpCER) of 11.56%, improving by 72.49%.

Objective: This review explores the trustworthiness of multimodal artificial intelligence (AI) systems, specifically focusing on vision-language tasks. It addresses critical challenges related to fairness, transparency, and ethical implications in these systems, providing a comparative analysis of key tasks such as Visual Question Answering (VQA), image captioning, and visual dialogue. Background: Multimodal models, particularly vision-language models, enhance artificial intelligence (AI) capabilities by integrating visual and textual data, mimicking human learning processes. Despite significant advancements, the trustworthiness of these models remains a crucial concern, particularly as AI systems increasingly confront issues regarding fairness, transparency, and ethics. Methods: This review examines research conducted from 2017 to 2024 focusing on forenamed core vision-language tasks. It employs a comparative approach to analyze these tasks through the lens of trustworthiness, underlining fairness, explainability, and ethics. This study synthesizes findings from recent literature to identify trends, challenges, and state-of-the-art solutions. Results: Several key findings were highlighted. Transparency: Explainability of vision language tasks is important for user trust. Techniques, such as attention maps and gradient-based methods, have successfully addressed this issue. Fairness: Bias mitigation in VQA and visual dialogue systems is essential for ensuring unbiased outcomes across diverse demographic groups. Ethical Implications: Addressing biases in multilingual models and ensuring ethical data handling is critical for the responsible deployment of vision-language systems. Conclusion: This study underscores the importance of integrating fairness, transparency, and ethical considerations in developing vision-language models within a unified framework.

This paper introduces the shapr R package, a versatile tool for generating Shapley value based prediction explanations for machine learning and statistical regression models. Moreover, the shaprpy Python library brings the core capabilities of shapr to the Python ecosystem. Shapley values originate from cooperative game theory in the 1950s, but have over the past few years become a widely used method for quantifying how a model's features/covariates contribute to specific prediction outcomes. The shapr package emphasizes conditional Shapley value estimates, providing a comprehensive range of approaches for accurately capturing feature dependencies -- a crucial aspect for correct model explanation, typically lacking in similar software. In addition to regular tabular data, the shapr R package includes specialized functionality for explaining time series forecasts. The package offers a minimal set of user functions with sensible default values for most use cases while providing extensive flexibility for advanced users to fine-tune computations. Additional features include parallelized computations, iterative estimation with convergence detection, and rich visualization tools. shapr also extends its functionality to compute causal and asymmetric Shapley values when causal information is available. Overall, the shapr and shaprpy packages aim to enhance the interpretability of predictive models within a powerful and user-friendly framework.

The increasing volume of online discussions requires advanced automatic content moderation to maintain responsible discourse. While hate speech detection on social media is well-studied, research on German-language newspaper forums remains limited. Existing studies often neglect platform-specific context, such as user history and article themes. This paper addresses this gap by developing and evaluating binary classification models for automatic content moderation in German newspaper forums, incorporating contextual information. Using LSTM, CNN, and ChatGPT-3.5 Turbo, and leveraging the One Million Posts Corpus from the Austrian newspaper Der Standard, we assess the impact of context-aware models. Results show that CNN and LSTM models benefit from contextual information and perform competitively with state-of-the-art approaches. In contrast, ChatGPT's zero-shot classification does not improve with added context and underperforms.

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning datasets, typically designed for powerful LLMs, often lead to degraded performance when directly applied to weaker models. In this work, we introduce Dynamic Adaptation of Reasoning Trajectories (DART), a novel data adaptation framework that bridges the capability gap between expert reasoning trajectories and diverse SLMs. Instead of uniformly imitating expert steps, DART employs a selective imitation strategy guided by step-wise adaptability estimation via solution simulation. When expert steps surpass the student's capacity -- signaled by an Imitation Gap -- the student autonomously explores alternative reasoning paths, constrained by outcome consistency. We validate DART across multiple reasoning benchmarks and model scales, demonstrating that it significantly improves generalization and data efficiency over static fine-tuning. Our method enhances supervision quality by aligning training signals with the student's reasoning capabilities, offering a scalable solution for reasoning alignment in resource-constrained models.

Terpenoids repre sent a pivotal class of natural products that have garnered su stained scientific interest for over 150 years . However, the inherently interdisciplinary nature of terpenoid research -- spanning fields such as chemistry, pharmacology, and biology -- poses significant challenges in integrat ing and communicati ng domain - specific knowledge across disciplines . To bridge this gap, we present TeroSeek, first by systematically extracting key scientific data and findings from terpenoid - related literature pub lished over the past two decades to construct a cura ted knowledge base (KB), and then further develop ing an intelligent question - answering chatbot and web service powered by an AI - accelerated retrieval - augmented generation (RAG) framework . TeroSeek en able s rapid access to structured, high - quality information and accurately respon ds to a wide range of terpenoid - related queries, demonstrat ing superior performance over general - purpose large language models (LLMs) in various application scenarios . T here fore, we believe that TeroSeek serves as a powerful domain - specific expert model to support the multidisciplinary terpenoid research community . The TeroSeek web service is publicly accessible at http://teroseek.qmclab.com .