6 papers · 1 filter
Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
Boyi Deng, Xu Wang, Yaoning Wang +15
Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, limiting our ability to inspec…
SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs
Boyi Deng, Yu Wan, Baosong Yang +3
Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to u…
Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders
Boyi Deng, Yu Wan, Yidan Zhang +2
The mechanisms behind multilingual capabilities in Large Language Models (LLMs) have been examined using neuron-based or internal-activation-based methods. However, these methods o…
P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs
Yidan Zhang, Yu Wan, Boyi Deng +6
Recent advancements in large language models (LLMs) showcase varied multilingual capabilities across tasks like translation, code generation, and reasoning. Previous assessments of…
CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG
Boyi Deng, Wenjie Wang, Fengbin Zhu +2
Retrieval-Augmented Generation (RAG) can alleviate hallucinations of Large Language Models (LLMs) by referencing external documents. However, the misinformation in external documen…
Attack Prompt Generation for Red Teaming and Defending Large Language Models
Boyi Deng, Wenjie Wang, Fuli Feng +3
Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or au…