Publications (16)
K-AID: Enhancing Pre-trained Language Models with Domain Knowledge for Question Answering
Fu Sun, Feng-Lin Li, Ruize Wang +3
Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice…
AMTSS: An Adaptive Multi-Teacher Single-Student Knowledge Distillation Framework For Multilingual Language Inference
Qianglong Chen, Feng Ji, Feng-Lin Li +4
Knowledge distillation is of key importance to launching multilingual pre-trained language models for real applications. To support cost-effective language inference in multilingua…
AliMe KG: Domain Knowledge Graph Construction and Application in E-commerce
Feng-Lin Li, Hehong Chen, Guohai Xu +4
Pre-sales customer service is of importance to E-commerce platforms as it contributes to optimizing customers' buying process. To better serve users, we propose AliMe KG, a domain…
Service Intelligence Oriented Distributed Data Stream Integration
Feng-Lin Li, Chi-Hung Chi, Yue Wang +1
Software as a service (SaaS) has recently enjoyed much attention as it makes the use of software more convenient and cost-effective. At the same time, the arising of users' expecta…
AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience
Feng-Lin Li, Minghui Qiu, Haiqing Chen +9
We present AliMe Assist, an intelligent assistant designed for creating an innovative online shopping experience in E-commerce. Based on question answering (QA), AliMe Assist offer…
AliMe KBQA: Question Answering over Structured Knowledge for E-commerce Customer Service
Feng-Lin Li, Weijia Chen, Qi Huang +1
With the rise of knowledge graph (KG), question answering over knowledge base (KBQA) has attracted increasing attention in recent years. Despite much research has been conducted on…
Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration
Xin Mao, Feng-Lin Li, Huimin Xu +2
While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding…
AliMe MKG: A Multi-modal Knowledge Graph for Live-streaming E-commerce
Guohai Xu, Hehong Chen, Feng-Lin Li +6
Live streaming is becoming an increasingly popular trend of sales in E-commerce. The core of live-streaming sales is to encourage customers to purchase in an online broadcasting ro…
Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
Huimin Xu, Xin Mao, Feng-Lin Li +4
Direct Preference Optimization (DPO) often struggles with long-chain mathematical reasoning. Existing approaches, such as Step-DPO, typically improve this by focusing on the first…
DictBERT: Dictionary Description Knowledge Enhanced Language Model Pre-training via Contrastive Learning
Qianglong Chen, Feng-Lin Li, Guohai Xu +3
Although pre-trained language models (PLMs) have achieved state-of-the-art performance on various natural language processing (NLP) tasks, they are shown to be lacking in knowledge…
Desiree - a Refinement Calculus for Requirements Engineering
Feng-Lin Li, John Mylopoulos
The requirements elicited from stakeholders suffer from various afflictions, including informality, incompleteness, ambiguity, vagueness, inconsistencies, and more. It is the task…
SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation
Huimin Xu, Xin Mao, Feng-Lin Li +4
Process Reward Models (PRMs) have demonstrated promising results in mathematical reasoning, but existing process annotation approaches, whether through human annotations or Monte C…
REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training
Fangkai Jiao, Yangyang Guo, Yilin Niu +3
Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned…
A Model-based Approach for Effective Service Delivery
Feng-Lin Li, Chi-Hung Chi
With the prevalence of X-as-a-Service (e.g., software as a service, platform as a service, infrastructure as a service, etc.) and users' growing demand on good services, QoS (Quali…
Desiree: a Refinement Calculus for Requirements Problems
Feng-Lin Li, Alexander Borgida, Giancarlo Guizzardi +3
The requirements elicited from stakeholders are typically informal, incomplete, ambiguous, and inconsistent. It is the task of Requirements Engineering to transform them into an el…
As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
Xin Mao, Feng-Lin Li, Huimin Xu +3
Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimizat…