ConsJudge method improves RAG model evaluation consistency, enhancing LLM judgment accuracy.

Shuliang Liu, Xinze Li, Zhenghao Liu et al.

Proposes Self-Certainty, a KL-divergence-based metric leveraging LLM output probabilities for scalable Best-of-N response selection without external reward models.

Zhewei Kang, Xuandong Zhao, Dawn Song

This paper systematically explores the design space for info extraction from layout-rich documents using LLMs, introducing LayIE-LLM and achieving up to 37.5 F1 improvement.

Gaye Colakoglu, Gürkan Solmaz, Jonathan Fürst

Proposes multimodal LLMs for zero-shot time series anomaly detection; introduces VisualTimeAnomaly benchmark; finds coarse anomalies better detected than fine ones.

Xiongxiao Xu, Haoran Wang, Yueqing Liang et al.

AutoLogi generates logic puzzles with program verification and controllable difficulty, evaluating LLM reasoning from 35% to 73%.

Qin Zhu, Fei Huang, Runyu Peng et al.

CODESYNC enhances LLMs' code synchronization by updating Python library APIs in real-time.

Chenlong Wang, Zhaoyang Chu, Zhengxiang Cheng et al.

Proposes CodeCriticBench, a comprehensive benchmark for large language models' code critique, combining basic and fine-grained multi-task evaluation with 4,300 samples.

Alexander Zhang, Marcus Dong, Jiaheng Liu et al.

ALFA framework decomposes question quality into attributes, synthesizes data, and uses preference optimization to reduce diagnostic errors by 56.6%.

Shuyue Stella Li, Jimin Mun, Faeze Brahman et al.

Introduces FUR framework using parameter unlearning to evaluate reasoning faithfulness; experiments show effective identification of key reasoning steps.

Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasović et al.

HippoRAG 2 leverages enhanced Passage integration and online LLM optimization, achieving 7% improvement in associative memory and superior factual and sense-making capabilities over standard RAG.

Bernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi et al.

Logic-RL employs rule-based reinforcement learning trained on synthetic logic puzzles, achieving 125% improvement on AIME and 38% on AMC benchmarks with only 5K puzzles.

Tian Xie, Zitian Gao, Qingnan Ren et al.

Introduced SUnsET dataset to enhance evidence citation accuracy in long-context query summarization.

Dustin Wright, Zain Muhammad Mujahid, Lu Wang et al.

Proposes education-inspired generative and explanation-based MCQA formats, addressing leakage, bias, and difficulty saturation.

Nishant Balepur, Rachel Rudinger, Jordan Lee Boyd-Graber

Enhanced long-context understanding via supervised CoT reasoning; GPT-4o-mini w/ PAI improves 20% on Loong benchmark.

Jingyang Lin, Andy Wong, Tian Xia et al.

Proposes MeCo, a meta-cognition-based adaptive tool-use method, improving decision accuracy by 10-15% and reducing unnecessary calls by 20-25%.

Wenjun Li, Dexun Li, Kuicai Dong et al.

This study evaluates LLMs on real-world mathematical definitions, introduces Def_Wiki and Def_ArXiv datasets, and enhances performance via feedback and grounding strategies.

Lan Zhang, Marco Valentino, Andre Freitas

Explores scaling laws for upscaling neural networks, revealing relationships between model size and performance.

Ayan Sengupta, Yash Goel, Tanmoy Chakraborty

LLMs in medicine show promise but face challenges like hallucination management and multimodal integration.

Wenxuan Wang, Zizhan Ma, Zheng Wang et al.

TituLLMs, a pioneering Bangla LLM with 1B and 3B parameters, uses extended tokenizer and 37B token dataset, outperforming multilingual versions in key tasks.

Shahriar Kabir Nahin, Rabindra Nath Nandi, Sagor Sarker et al.

CMCTS framework enhances LLM's mathematical reasoning with constrained action space; 7B model achieves 83.4% accuracy.

Qingwen Lin, Boyan Xu, Guimin Hu et al.