7 papers
Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
Guangyue Peng, Zongchao Chen, Wen Luo +9
Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but answer-visible generation can justify a pre-committed answer rather than derive…
Generative Retrieval via Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference Optimization
Chenghao Liu, Yu Zhang, Zhongtao Jiang +7
Embedding-based retrieval ranks items by their similarity to a query in a shared vector space and usually aims to return the highest-scoring items. In many production settings this…
Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts
Chen Yang, Guangyue Peng, Jiaying Zhu +12
We present Nanbeige4.1-3B, a unified generalist language model that simultaneously achieves strong agentic behavior, code generation, and general reasoning with only 3B parameters.…
PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning
Ruixiang Feng, Yuntao Wen, Silin Zhou +14
Language Reasoning Models (LRMs) achieve strong performance by scaling test-time computation but often suffer from ``overthinking'', producing excessively long reasoning traces tha…
Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models
Chen Yang, Guangyue Peng, Jiaying Zhu +16
We present Nanbeige4-3B, a family of small-scale but high-performing language models. Pretrained on 23T high-quality tokens and finetuned on over 30 million diverse instructions, w…
ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset
Chen Yang, Ran Le, Yun Xing +5
Large Language Model (LLM) agents have developed rapidly in recent years to solve complex real-world problems using external tools. However, the scarcity of high-quality trajectori…