6 papers
What Are They Talking About? A Benchmark of Knowledge-Grounded Discussion Summarization
Weixiao Zhou, Junnan Zhu, Gengyao Li +4
Traditional dialogue summarization primarily focuses on dialogue content, assuming it comprises adequate information for a clear summary. However, this assumption often fails for d…
ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs
Feng He, Zijun Chen, Xinnian Liang +4
Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought (Long CoT) reasoning have demonstrated remarkable cross-domain generalization capabilities. Howe…
AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning
Chenwei Lou, Zewei Sun, Xinnian Liang +6
Large Language Models (LLMs) have demonstrated remarkable capabilities but often face challenges with tasks requiring sophisticated reasoning. While Chain-of-Thought (CoT) promptin…
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
ByteDance Seed, :, Jiaze Chen +267
We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 8…
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
Bing Wang, Changyu Ren, Jian Yang +8
Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on "huge" databases and complex user questions that require multi-step reasoning. Moreo…
SCM: Enhancing Large Language Model with Self-Controlled Memory Framework
Bing Wang, Xinnian Liang, Jian Yang +6
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in…