2 citations · 3 across the 8 of their papers we have counts for
11 papers
Reflective Recovery: A Self-Supervised Method for Reasoning by Learning from Mistakes
Qirui Chen, Renjie Pi, Jiahui Gao +1
Data-driven fine-tuning is widely adopted to enhance reasoning in Large Language Models (LLMs) due to its simplicity and efficiency. However, mainstream imitation learning methods…
Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach
Che Shen, Junwei Su, Lingpeng Kong +1
Reliable post-hoc evaluation asks whether already generated text satisfies a target criterion after generation. In this paper we study a focused frozen-embedding setting using prin…
ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation
Jingqi Zhou, Sheng Wang, Dezhao Deng +9
LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidity forces a trade-off between do…
Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models
Jiyue Jiang, Alfred Kar Yin Truong, Yanyu Chen +7
High-quality data resources play a crucial role in learning large language models (LLMs), particularly for low-resource languages like Cantonese. Despite having more than 85 millio…
TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning
Sheng Wang, Pengan Chen, Jingqi Zhou +7
Model customization necessitates high-quality and diverse datasets, but acquiring such data remains time-consuming and labor-intensive. Despite the great potential of large languag…
QSpec: Speculative Decoding with Complementary Quantization Schemes
Juntao Zhao, Wenhao Lu, Sheng Wang +2
Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs). While activation-weight joint quantization enables efficient l…
MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards
Sheng Wang, Liheng Chen, Pengan Chen +5
The rapid scaling of large language models necessitates more lightweight finetuning methods to reduce the explosive GPU memory overhead when numerous customized models are served s…
How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models
Jiyue Jiang, Pengan Chen, Liheng Chen +5
The rapid evolution of large language models (LLMs) has transformed the competitive landscape in natural language processing (NLP), particularly for English and other data-rich lan…
Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting
Jiyue Jiang, Liheng Chen, Sheng Wang +3
Existing dialogue data augmentation (DA) techniques predominantly focus on augmenting utterance-level dialogues, which makes it difficult to take dialogue contextual information in…
LoRA Meets Dropout under a Unified Framework
Sheng Wang, Liheng Chen, Jiyue Jiang +3
With the remarkable capabilities, large language models (LLMs) have emerged as essential elements in numerous NLP applications, while parameter-efficient finetuning, especially LoR…
PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA
Sheng Wang, Boyang Xue, Jiacheng Ye +4
With the rapid scaling of large language models (LLMs), serving numerous low-rank adaptations (LoRAs) concurrently has become increasingly impractical, leading to unaffordable cost…