68 citations · 77 across the 12 of their papers we have counts for
14 papers
Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents
Wenyu Huang, Xinyu Hou, Pavlos Vougiouklis +2
Search agents enable Large Language Models (LLMs) to iteratively retrieve and use information for complex multi-hop questions. Reinforcement Learning with Verifiable Rewards (RLVR)…
Self-Play Search Distillation for Large Language Model Reasoning
Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni +5
Improving reasoning abilities in Large Language Models (LLMs) requires high-quality data that exposes difficult decisions, competing alternatives, and their consequences. Data scar…
OpenSIR: Open-Ended Self-Improving Reasoner
Wai-Chung Kwan, Joshua Ong Jun Leang, Pavlos Vougiouklis +3
Recent advances in large language model (LLM) reasoning through reinforcement learning rely on annotated datasets for verifiable rewards, which may limit models' ability to surpass…
Millions of -s: Extending GraphRAG to Millions of Documents
Zhili Shen, Chenxin Diao, Pascual Merita +2
Recent studies have explored graph-based approaches to retrieval-augmented generation, leveraging structured or semi-structured information -- such as entities and their relations…
Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation
Wenyu Huang, Pavlos Vougiouklis, Mirella Lapata +1
Multi-hop Question Answering (MHQA) adds layers of complexity to question answering, making it more challenging. When Language Models (LMs) are prompted with multiple search result…
An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs
Kaustubh Vyas, Damien Graux, Sébastien Montella +5
In recent advancements, large language models (LLMs) have exhibited proficiency in code generation and chain-of-thought reasoning, laying the groundwork for tackling automatic form…
GeAR: Graph-enhanced Agent for Retrieval-augmented Generation
Zhili Shen, Chenxin Diao, Pavlos Vougiouklis +12
Retrieval-augmented Generation (RAG) relies on effective retrieval capabilities, yet traditional sparse and dense retrievers inherently struggle with multi-hop retrieval scenarios.…
From An LLM Swarm To A PDDL-Empowered HIVE: Planning Self-Executed Instructions In A Multi-Modal Jungle
Kaustubh Vyas, Damien Graux, Yijun Yang +8
In response to the call for agent-based solutions that leverage the ever-increasing capabilities of the deep models' ecosystem, we introduce Hive -- a comprehensive solution for kn…
Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning
Zhili Shen, Pavlos Vougiouklis, Chenxin Diao +3
We focus on Text-to-SQL semantic parsing from the perspective of retrieval-augmented generation. Motivated by challenges related to the size of commercial database schemata and the…
Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts
Wenyu Huang, Guancheng Zhou, Mirella Lapata +3
Although Large Language Models (LLMs) are effective in performing various NLP tasks, they still struggle to handle tasks that require extensive, real-world knowledge, especially wh…
A Usage-centric Take on Intent Understanding in E-Commerce
Wendi Zhou, Tianyi Li, Pavlos Vougiouklis +2
Identifying and understanding user intents is a pivotal task for E-Commerce. Despite its essential role in product recommendation and business user profiling analysis, intent under…
Task-specific Pre-training and Prompt Decomposition for Knowledge Graph Population with Language Models
Tianyi Li, Wenyu Huang, Nikos Papasarantopoulos +2
We present a system for knowledge graph population with Language Models, evaluated on the Knowledge Base Construction from Pre-trained Language Models (LM-KBC) challenge at ISWC 20…
Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
Lucie-Aimée Kaffee, Hady Elsahar, Pavlos Vougiouklis +4
While Wikipedia exists in 287 languages, its content is unevenly distributed among them. In this work, we investigate the generation of open domain Wikipedia summaries in underserv…
Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
Pavlos Vougiouklis, Hady Elsahar, Lucie-Aimée Kaffee +4
Most people do not interact with Semantic Web data directly. Unless they have the expertise to understand the underlying technology, they need textual or visual interfaces to help…