6 citations · 21 across the 17 of their papers we have counts for
9 papers · 1 filter
Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes
Luc Hazenoot, Zhaochun Ren, Amirhossein Zohrehvand
Recent work shows that Large Language Models (LLMs) encode more information in their activations than they show in their responses. We ask whether the information contained in acti…
Evolution without Large Models: Training Language Model with Task Principles
Minghang Zhu, Shen Gao, Zhengliang Shi +5
A common training approach for language models involves using a large-scale language model to expand a human-provided dataset, which is subsequently used for model training.This me…
Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning
Yukun Zhao, Lingyong Yan, Zhenyang Li +4
Large language models have achieved remarkable success in various tasks. However, it is challenging for them to learn new tasks incrementally due to catastrophic forgetting. Existi…
Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
Zhengliang Shi, Shen Gao, Lingyong Yan +6
Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extend their utility, enabling them to solve practical tasks. Previous methods ma…
Improving the Robustness of Large Language Models via Consistency Alignment
Yukun Zhao, Lingyong Yan, Weiwei Sun +6
Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal…
How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
Tianjie Ju, Weiwei Sun, Wei Du +3
Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on…
KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
Yougang Lyu, Lingyong Yan, Shuaiqiang Wang +6
Despite their success at many natural language processing (NLP) tasks, large language models still struggle to effectively leverage knowledge for knowledge-intensive tasks, manifes…
DiQAD: A Benchmark Dataset for End-to-End Open-domain Dialogue Assessment
Yukun Zhao, Lingyong Yan, Weiwei Sun +5
Dialogue assessment plays a critical role in the development of open-domain dialogue systems. Existing work are uncapable of providing an end-to-end and human-epistemic assessment…
Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method
Yukun Zhao, Lingyong Yan, Weiwei Sun +6
Large Language Models (LLMs) have shown great potential in Natural Language Processing (NLP) tasks. However, recent literature reveals that LLMs generate nonfactual responses inter…