14 papers
From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training
Zishang Jiang, Tingyun Li, Jinyi Han +7
Reinforcement learning (RL) has become a widely adopted technique for improving large language models (LLMs) on complex tasks. Despite this progress, existing RL methods still face…
MADE: Beyond Scoring via a Multilingual Agentic Diagnosing Engine for Fine-Grained Evaluation Insights
Yilun Liu, Miao Zhang, Shimin Tao +9
Multilingual and multicultural benchmarks now cover dozens of languages and model families, but the resulting score landscapes remain metric-rich and insight-poor, necessitating fi…
The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models
Yilun Liu, Chunguang Zhao, Mengyao Piao +14
Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current benchmarks face three critical li…
MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis
Zixiong Yu, Jun Rao, Guhan Chen +5
Synthesizing high-quality mathematical reasoning data without human priors remains a significant challenge. Current approaches typically rely on seed data mutation or simple prompt…
Mining or Synthesis? Rethinking Exploration Efficiency in Iterative Alignment of Mathematical Reasoning
Jun Rao, Zixiong Yu, Xuebo Liu +6
Iterative Direct Preference Optimization (DPO) has emerged as a widely used paradigm for aligning Large Language Models on reasoning tasks. Existing approaches typically rely on Be…
Why Did Apple Fall: Evaluating Curiosity in Large Language Models
Haoyu Wang, Sihang Jiang, Yuyan Chen +4
Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent advancements of large language models (LLMs) in natural language processing have…
ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models
Yueqian Wang, Xiaojun Meng, Yifan Wang +2
With the growing research focus on multimodal dialogue systems, the capability for proactive interaction is gradually gaining recognition. As an alternative to conventional turn-by…
Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs
Yehui Tang, Yichun Yin, Yaoyuan Wang +71
Sparse large language models (LLMs) with Mixture of Experts (MoE) and close to a trillion parameters are dominating the realm of most capable language models. However, the massive…
Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning
Jun Rao, Xuebo Liu, Hexuan Deng +5
In mathematical reasoning, data selection strategies predominantly rely on static, externally defined metrics, which fail to adapt to the evolving capabilities of models during tra…
Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs
Yichun Yin, Wenyong Huang, Kaikai Song +49
We present Pangu Ultra, a Large Language Model (LLM) with 135 billion parameters and dense Transformer modules trained on Ascend Neural Processing Units (NPUs). Although the field…
ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
Jianxin Liang, Xiaojun Meng, Huishuai Zhang +3
Video Question Answering (VideoQA) is a challenging task that requires understanding complex visual and temporal relationships within videos to answer questions accurately. In this…
CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory
Haokun Zhao, Jinyi Han, Jiaqing Liang +3
Large Language Models (LLMs) have achieved significant advancements, but the increasing complexity of tasks and higher performance demands highlight the need for continuous improve…
Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding
Yueqian Wang, Xiaojun Meng, Yuxuan Wang +3
Multi-modal multi-party conversation (MMC) is a less studied yet important topic of research due to that it well fits real-world scenarios and thus potentially has more widely-used…
VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
Yueqian Wang, Xiaojun Meng, Yuxuan Wang +4
Recent researches on video large language models (VideoLLM) predominantly focus on model architectures and training datasets, leaving the interaction format between the user and th…