Ho-fung Leung

From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development

Muzhi Li, Jianpeng Qi, Yihong Wu, Minghao Zhao et autres

Retrieval-augmented generation (RAG) agent development is hindered by the lack of executable ground-truth agent-environment interaction trajectories. Existing datasets provide questions, answers, and evidence, but lack fine-grained supervision for retriever invocation, dynamic planning, and stepwise decision-making. Reinforcement learning offers a potential solution, but …

hk, ca, gb, se (code pays fourni par la source)

Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning

Yihong Wu, Liheng Ma, Muzhi Li, Jiaming Zhou et autres

Large Language Models (LLMs) equipped with modern Retrieval-Augmented Generation (RAG) systems often employ multi-turn interaction pipelines to interface with search engines for complex reasoning tasks. However, such multi-turn interactions inevitably produce long intermediate contexts, as context length grows exponentially with exploration depth. …

ca, hk, se, cn (code pays fourni par la source)

ADRA-Bank: A Modular Benchmark for Academic Deep Research Agents

Zhihan Guo, Feiyang Xu, Yifan Li, Muzhi Li et autres

A surge in academic publications calls for automated deep research (DR) systems, but accurately evaluating them is still an open problem. First, existing benchmarks often focus narrowly on retrieval while neglecting high-level planning and reasoning. Second, existing benchmarks favor general domains over …

Type-agnostic and form-oriented deductive conclusion generation

Xin Wu, Yuqi Bu, Yi Cai, Yifei Chen et autres

cn, us (code pays fourni par la source)

An Unsupervised Fake News Detection Framework Based on Structural Contrastive Learning

Yajie Guo, Shujuan Ji, Xianwen Fang, Dickson K.W. Chiu et autres

Abstract Recently, fake news detection on social media (SM) has attracted a lot of attention. With the emergence of fake news at a breakneck pace, the massive spread of fake news has had a serious impact in our society. The authenticity of …

es, cn, hk (code pays fourni par la source)

PromptWise: Online Learning for Cost-Aware Prompt Assignment in Generative Models

Xiaoyan Hu, Lauren Pick, Ho-fung Leung, Farzan Farnia

The rapid advancement of generative AI has provided users with a wide range of well-trained models to address diverse prompts. When selecting a model for a given prompt, users should weigh not only its performance but also its service cost. However, existing …

VirtualHAR: Virtual Sensing Device and Correlation-Based Learning Approach for Multiwearable Sensing Device-Based Human Activity Recognition

Nafees Ahmad, Ho-fung Leung, Farzan Farnia

Human activity recognition (HAR) is a prominent research direction in ubiquitous computing. Current state-of-the-art HAR models achieve great success by learning the correlations between the regions of the body parts by using the attached sensing devices for feature extraction. However, explicitly computing …

hk (code pays fourni par la source)

Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning

Muzhi Li, Cehao Yang, Chengjin Xu, Zixing Song et autres

Inductive knowledge graph completion (KGC) aims to predict missing triples with unseen entities. Recent works focus on modeling reasoning paths between the head and tail entity as direct supporting evidence. However, these methods depend heavily on the existence and quality of reasoning …

hk, us, gb (code pays fourni par la source)

Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

Muzhi Li, Cehao Yang, Chengjin Xu, Xuhui Jiang et autres

Muzhi Li, Cehao Yang, Chengjin Xu, Xuhui Jiang, Yiyan Qi, Jian Guo, Ho-fung Leung, Irwin King. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

hk, us, ca (code pays fourni par la source)

Assessing private solutions to collective action problems in a 34-nation study

Eugene Malthouse, Charlie Pilgrim, Daniel Sgroi, Michela Accerenzi et autres

gb, bo, es, pl, Afrique du Sud, nl, ru, in, uy, kr, jp, ph, it, cn, hu, us, at, fr, lb, de, cz, Ghana, hk, dk, au, me, do, id, Sénégal, ca, tw, ch (code pays fourni par la source)

Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

Muzhi Li, Cehao Yang, Chengjin Xu, Xuhui Jiang et autres

The Knowledge Graph Completion~(KGC) task aims to infer the missing entity from an incomplete triple. Existing embedding-based methods rely solely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities. On the other hand, text-based methods struggle …

Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning

Muzhi Li, Cehao Yang, Chengjin Xu, Zixing Song et autres

Inductive knowledge graph completion (KGC) aims to predict missing triples with unseen entities. Recent works focus on modeling reasoning paths between the head and tail entity as direct supporting evidence. However, these methods depend heavily on the existence and quality of reasoning …