6 papers
Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
Shouren Wang, Wang Yang, Xianxuan Long +3
Hybrid thinking enables LLMs to switch between reasoning and direct answering, offering a balance between efficiency and reasoning capability. Yet our experiments reveal that curre…
Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs
Yao Fu, Runchao Li, Xianxuan Long +4
Neural network pruning has emerged as a promising approach for deploying LLMs in low-resource scenarios while preserving downstream task performance. However, for the first time, w…
Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs
Yao Fu, Xianxuan Long, Runchao Li +5
Quantization enables efficient deployment of large language models (LLMs) in resource-constrained environments by significantly reducing memory and computation costs. While quantiz…
FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression
Runchao Li, Yao Fu, Mu Sheng +3
The efficacy of Large Language Models (LLMs) in long-context tasks is often hampered by the substantial memory footprint and computational demands of the Key-Value (KV) cache. Curr…
When Truthful Representations Flip Under Deceptive Instructions?
Xianxuan Long, Yao Fu, Runchao Li +4
Large language models (LLMs) tend to follow maliciously crafted instructions to generate deceptive responses, posing safety challenges. How deceptive instructions alter the interna…
Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language Models
Yao Fu, Yin Yu, Xiaotian Han +4
Knowledge distillation (KD) has become a widely adopted approach for compressing large language models (LLMs) to reduce computational costs and memory footprints. However, the avai…