7 papers
One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems
Mingzhe Li, Jing Xiang, Enguo Zhou +5
Dialogue systems in e-commerce scenarios often need to satisfy multiple objectives: accurately reasoning over user profiles (e.g., eligibility, credit limit) to ensure correct deci…
Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matching
Mingzhe Li, Jing Xiang, Qishen Zhang +2
Knowledge distillation typically involves transferring knowledge from a Large Language Model (LLM) to a Smaller Language Model (SLM). However, in tasks such as text matching, fine-…
Detoxifying Large Language Models via Knowledge Editing
Mengru Wang, Ningyu Zhang, Ziwen Xu +7
This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with va…
Multi-Intent Attribute-Aware Text Matching in Searching
Mingzhe Li, Xiuying Chen, Jing Xiang +6
Text matching systems have become a fundamental service in most searching platforms. For instance, they are responsible for matching user queries to relevant candidate items, or re…
A Multi-Granularity-Aware Aspect Learning Model for Multi-Aspect Dense Retrieval
Xiaojie Sun, Keping Bi, Jiafeng Guo +5
Dense retrieval methods have been mostly focused on unstructured text and less attention has been drawn to structured data with various aspects, e.g., products with aspects such as…
Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models
Yue Wang, Xinrui Wang, Juntao Li +5
Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks. The success of instruction tuning dep…