11 papers
UltraIF: Advancing Instruction Following from the Wild
Kaikai An, Li Sheng, Ganqu Cui +4
Instruction-following made modern large language models (LLMs) helpful assistants. However, the key to taming LLMs on complex instructions remains mysterious, for that there are hu…
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation
Kaikai An, Fangkai Yang, Liqun Li +10
Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid '5Ws' questions. However, significant chall…
GATEAU: Selecting Influential Samples for Long Context Alignment
Shuzheng Si, Haozhe Zhao, Gang Chen +7
Aligning large language models to handle instructions with extremely long contexts has yet to be fully investigated. Previous studies have attempted to scale up the available data…
Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative Learning
Shuzheng Si, Helan Hu, Haozhe Zhao +4
Distantly-Supervised Named Entity Recognition (DS-NER) is widely used in real-world scenarios. It can effectively alleviate the burden of annotation by matching entities in existin…
Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints
Kaikai An, Shuzheng Si, Helan Hu +4
Semantic Parsing aims to capture the meaning of a sentence and convert it into a logical, structured form. Previous studies show that semantic parsing enhances the performance of s…
Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering
Shuzheng Si, Haozhe Zhao, Gang Chen +9
Training LLMs on data containing unfamiliar knowledge during the instruction tuning stage can encourage hallucinations. To address this challenge, we introduce NOVA, a novel framew…