MCJudgeBench evaluates LLM judge accuracy and stability at constraint level, distinguishing intrinsic and procedural inconsistencies.

Jaeyun Lee, Junyoung Koh, Zeynel Tok et al.

Introduces InfoLaw, a data-aware scaling law using information theory to predict large language model performance with quality-weighted data and repetition, achieving 0.15% loss prediction error.

Fengze Liu, Weidong Zhou, Binbin Liu et al.

Decoupling Exploration and Commitment with Calibration-Aware Generation boosts factuality by up to 13% in long-form outputs.

Wen Luo, Guangyue Peng, Liang Wang et al.

EPIC replaces textual demonstrations with embeddings, boosting LLMs as text encoders with reduced token overhead, achieving state-of-the-art on MTEB.

Ailiang Lin, Zhuoyun Li, Keyu Mao et al.

MathArena extends to a dynamic platform, achieving 98% on 2026 USAMO and 74% on research problems, tracking LLM progress in mathematical reasoning.

Jasper Dekoninck, Nikola Jovanović, Tim Gehrunger et al.

DriftBench evaluates constraint adherence in multi-turn LLM ideation, revealing complexity inflation and constraint violations.

Garvin Kruthof

Proposed uxWeb dataset and uxCUA model achieve 25% improvement in automated GUI usability assessment accuracy, enabling scalable, data-driven evaluation.

Alice Gao, Weixi Tong, Rishab Vempati et al.

Sentiment and emotion classification of Indonesian e-commerce reviews using Multi-Task BiLSTM and AutoML, achieving high accuracy.

Hermawan Manurung, Ibrahim Al-Kahfi, Ahmad Rizqi et al.

SeaEvo enhances algorithm discovery via strategy space evolution, achieving 21% improvement in system optimization tasks.

Sichun Luo, Yi Huang, Haochen Luo et al.

OS-SPEAR toolkit systematically analyzes OS agents' safety, performance, efficiency, and robustness, revealing trade-offs between efficiency and safety.

Zheng Wu, Yi Hua, Zhaoyuan Huang et al.

Improving tabular retrieval robustness via representational stability using centroid averaging to reduce format-specific variance.

Kushal Raj Bhandari, Adarsh Singh, Jianxi Gao et al.

Introduces SSL, a three-layer structured skill representation, improving skill retrieval and risk assessment with 15-20% performance gains.

Qiliang Liang, Hansi Wang, Zhong Liang et al.

DeepSeek-V4 employs hybrid CSA and HCA attention, supports million-token contexts, reducing inference FLOPs to 27%, enabling ultra-long sequence processing.

DeepSeek-AI, Anyi Xu, Bangcai Lin et al.

AutoPyVerifier uses DAG search to automatically learn compact Python verifiers, improving target F1 by up to 55 points.

Pouya Pezeshkpour, Estevam Hruschka

Study reveals representational harms in LLM narratives against Global Majority nationalities using a QA model on 500,000 stories.

Ilana Nguyen, Harini Suresh, Thema Monroe-White et al.

Scaling large point-in-time language models (4B params, 1T tokens) narrows performance gap with unrestricted models, ensuring temporal validity and economic relevance.

Bryan Kelly, Semyon Malamud, Johannes Schwab et al.

CRAFT method enhances BLEU score by 2.13 points in English-Hindi translation through clustered regression for adaptive filtering.

Parthasarathi Panda, Asheswari Swain, Subhrakanta Panda

BERAG improves retrieval-augmented generation with Bayesian ensemble, significantly enhancing knowledge-based visual question answering performance.

Jinghong Chen, Jingbiao Mei, Guangyu Yang et al.

An LLM-assisted analysis of 30 multilingual YouTube videos shows that cultural health misinformation defeats prompt-only detection.

Anamta Khan, Ratna Kandala, Deepti et al.

EVENT5Ws: A large dataset for open-domain event extraction, manually annotated and statistically verified.

Praval Sharma, Ashok Samal, Leen-Kiat Soh et al.