2 citations · 7 across the 17 of their papers we have counts for
20 papers
Mitigating Context Interference for Reliable and Efficient Search Agents
Boyang Xue, Bin Wu, Shuofei Qiao +8
Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts…
UXBench: Benchmarking User Experience in AI Assistants
Mengze Hong, Xia Zeng, Zeyang Lei +27
As AI assistants serve millions of users daily, evaluating user experience (UX) beyond general model capability has become increasingly important. We present \textbf{UXBench}, the…
TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
Fangrui Huang, Souhad Chbeir, Arpandeep Khatua +8
Large language models (LLMs) are increasingly used for mental-health support; yet prevailing evaluation methods--fluency metrics, preference tests, and generic dialogue benchmarks-…
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…
DAST: Difficulty-Aware Self-Training on Large Language Models
Boyang Xue, Qi Zhu, Hongru Wang +8
Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' abilit…
Benchmarking Large Language Models on Multiple Tasks in Bioinformatics NLP with Prompting
Jiyue Jiang, Pengan Chen, Jiuming Wang +13
Large language models (LLMs) have become important tools in solving biological problems, offering improvements in accuracy and adaptability over conventional methods. Several bench…
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…
UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
Boyang Xue, Fei Mi, Qi Zhu +6
Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where…
Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration
Qintong Li, Jiahui Gao, Sheng Wang +6
Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data, leading to impressive performance across a range of downstream…
MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
Boyang Xue, Hongru Wang, Rui Wang +5
The tendency of Large Language Models (LLMs) to generate hallucinations raises concerns regarding their reliability. Therefore, confidence estimations indicating the extent of trus…
ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom
Jingqi Zhou, Sheng Wang, Jingwei Dong +6
Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on…
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…
MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
Boyang Xue, Hongru Wang, Rui Wang +6
The tendency of Large Language Models (LLMs) to generate hallucinations raises concerns regarding their reliability. Therefore, confidence estimations indicating the extent of trus…
A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment
Jiyue Jiang, Sheng Wang, Qintong Li +2
When communicating with elders with cognitive impairment, cognitive stimulation (CS) help to maintain the cognitive health of elders. Data sparsity is the main challenge in buildin…