14 papers
Dual-Vocabulary Language Model for Cross-Tokenizer Distillation
Kedi Chen, Chen Lin, Yutao Sun +1
On-policy distillation (OPD) bridges teacher supervision and student behavior, but different teacher-student tokenizers introduce misalignment in both input tokenization (#1) and o…
ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation
Chen Lin, Kedi Chen, Wei Zhang
On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-generated outputs (SGOs) equally r…
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design
Xu Guo, Qiming Ge, Jian Tong +8
Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (M…
MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing
Runze Li, Kedi Chen, Guwei Feng +3
Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning…
Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
Jianghao Yin, Qin Chen, Kedi Chen +3
Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation…
Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models
Kedi Chen, Zhikai Lei, Xu Guo +10
Large language models (LLMs) make remarkable progress in reasoning tasks. Among different reasoning modes, inductive reasoning, due to its better alignment with human learning, att…
A Survey of Inductive Reasoning for Large Language Models
Kedi Chen, Dezhao Ruan, Yuhao Dan +12
Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by i…
Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models
Chang Wang, Siyu Yan, Depeng Yuan +8
The generation of ad headlines plays a vital role in modern advertising, where both quality and diversity are essential to engage a broad range of audience segments. Current approa…
InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scaling
Peiji Li, Jiasheng Ye, Yongkang Chen +12
Large language models (LLMs) have revolutionized artificial intelligence by enabling complex reasoning capabilities. While recent advancements in reinforcement learning (RL) have p…
Code-Driven Inductive Synthesis: Enhancing Reasoning Abilities of Large Language Models with Sequences
Kedi Chen, Zhikai Lei, Fan Zhang +7
Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reas…
Complete Chess Games Enable LLM Become A Chess Master
Yinqi Zhang, Xintian Han, Haolong Li +2
Large language models (LLM) have shown remarkable abilities in text generation, question answering, language translation, reasoning and many other tasks. It continues to advance ra…
Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection
Kedi Chen, Qin Chen, Jie Zhou +7
Large Language Models (LLMs) are prone to hallucination with non-factual or unfaithful statements, which undermines the applications in real-world scenarios. Recent researches focu…
DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models
Kedi Chen, Qin Chen, Jie Zhou +2
Since large language models (LLMs) achieve significant success in recent years, the hallucination issue remains a challenge, numerous benchmarks are proposed to detect the hallucin…
A Regularization-based Transfer Learning Method for Information Extraction via Instructed Graph Decoder
Kedi Chen, Jie Zhou, Qin Chen +2
Information extraction (IE) aims to extract complex structured information from the text. Numerous datasets have been constructed for various IE tasks, leading to time-consuming an…