69 citations · 143 across the 33 of their papers we have counts for
40 papers
MOSAIC: Addressing Disproportionate Task-Modality Dependencies via Modality-Partitioned Gradient Routing
Aryan Chowdhury, Yizheng Sun, Thomas Carroll +1
In multi-task settings, combining multiple modalities allows task representations to draw on signals that a single modality alone would not capture. However, individual tasks may d…
Fewer Heads, Fewer Memories: Pruning Redundant Attention Heads Suppresses Verbatim Memorisation
Aryan Chowdhury, Riza Batista-Navarro
Large language models have been shown to memorise and reproduce verbatim sequences from their training data, raising concerns about privacy leakage, intellectual property exposure,…
SCODEL: Shared Canonical Ontology Definitions for Food Entity Linking and Ontology-Grounded Recipe Knowledge Graphs
Nuhu Ibrahim, Rishi Ravikumar, Ayuba Dauda +3
Identifying recipe entities and linking them to ontology concepts is fundamental for semantic recipe understanding. However, food mentions in recipes are often ambiguous, context-d…
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Siwei Wu, Jincheng Ren, Yizhi Li +12
Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience.…
MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL
Beiyu Xu, Zhenyu Wu, Jiaoyan Chen +1
Traditional Text-to-SQL research and benchmarks assume a known target database, overlooking settings in which a query must be routed within a large, heterogeneous database collecti…
Automatic Detection of Deaths from Social Networking Sites
Nuhu Ibrahim, Riza Batista-Navarro
This dissertation analysed and discussed the differences in linguistic characteristics between pre-mortem and post-mortem social media content, and reported machine learning (ML) c…
The BD-LSC Dataset: Facilitating the Benchmarking of Models for Lexical Semantic Change Detection in Slang and Standard Usage
Afnan Aloraini, Viktor Schlegel, Goran Nenadic +1
Automatic semantic change detection aims to identify how word meanings shift over time, offering insights into both linguistic and societal change. Despite recent progress in compu…
Are Reasoning Vision-Language Models Robust to Semantic Visual Distractions?
Yizheng Sun, Mochuan Zhan, Yanan Ma +10
Reasoning Vision-Language Models (VLMs) achieve strong performance on complex multimodal tasks, but reliable real-world application requires handling visual inputs that are messier…
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
Jincheng Ren, Siwei Wu, Yizhi Li +8
As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the in…
Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments
Siwei Wu, Yizhi Li, Yuyang Song +8
Training agentic models for terminal-based tasks critically depends on high-quality terminal trajectories that capture realistic long-horizon interactions across diverse domains. H…
Natural Context Drift Undermines the Natural Language Understanding of Large Language Models
Yulong Wu, Viktor Schlegel, Riza Batista-Navarro
How does the natural evolution of context paragraphs affect question answering in generative Large Language Models (LLMs)? To investigate this, we propose a framework for curating…
Natural Language Satisfiability: Exploring the Problem Distribution and Evaluating Transformer-based Language Models
Tharindu Madusanka, Ian Pratt-Hartmann, Riza Batista-Navarro
Efforts to apply transformer-based language models (TLMs) to the problem of reasoning in natural language have enjoyed ever-increasing success in recent years. The most fundamental…
Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
Hao Li, Yizheng Sun, Viktor Schlegel +3
Argument summarization aims to generate concise, structured representations of complex, multi-perspective debates. While recent work has advanced the identification and clustering…
Large Language Models in Argument Mining: A Survey
Hao Li, Viktor Schlegel, Yizheng Sun +2
Large Language Models (LLMs) have fundamentally reshaped Argument Mining (AM), shifting it from a pipeline of supervised, task-specific classifiers to a spectrum of prompt-driven,…
LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm
Siwei Wu, Yizhi Li, Xingwei Qu +7
Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks, yet their ability to generate long-form content remains poorly understoo…
Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study
Yizheng Sun, Hao Li, Chang Xu +4
Vision-Language Models (VLMs) are powerful yet computationally intensive for widespread practical deployments. To address such challenge without costly re-training, post-training a…
BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
Hao Li, Yu-Hao Huang, Chang Xu +5
Time-series Generation (TSG) is a prominent research area with broad applications in simulations, data augmentation, and counterfactual analysis. While existing methods have shown…
Pay Attention to Real World Perturbations! Natural Robustness Evaluation in Machine Reading Comprehension
Yulong Wu, Viktor Schlegel, Riza Batista-Navarro
As neural language models achieve human-comparable performance on Machine Reading Comprehension (MRC) and see widespread adoption, ensuring their robustness in real-world scenarios…
LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models
Yizheng Sun, Yanze Xin, Hao Li +3
Multi-modal Large Language Models (MLLMs) have achieved remarkable success by integrating visual and textual modalities. However, they incur significant computational overhead due…
TriG-NER: Triplet-Grid Framework for Discontinuous Named Entity Recognition
Rina Carines Cabral, Soyeon Caren Han, Areej Alhassan +3
Discontinuous Named Entity Recognition (DNER) presents a challenging problem where entities may be scattered across multiple non-adjacent tokens, making traditional sequence labell…
Learning to Generate and Evaluate Fact-checking Explanations with Transformers
Darius Feher, Abdullah Khered, Hao Zhang +2
In an era increasingly dominated by digital platforms, the spread of misinformation poses a significant challenge, highlighting the need for solutions capable of assessing informat…
Investigating a Benchmark for Training-set free Evaluation of Linguistic Capabilities in Machine Reading Comprehension
Viktor Schlegel, Goran Nenadic, Riza Batista-Navarro
Performance of NLP systems is typically evaluated by collecting a large-scale dataset by means of crowd-sourcing to train a data-driven model and evaluate it on a held-out portion…
Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation
Hao Li, Yuping Wu, Viktor Schlegel +8
With the recent advances of large language models (LLMs), it is no longer infeasible to build an automated debate system that helps people to synthesise persuasive arguments. Previ…
CANTONMT: Investigating Back-Translation and Model-Switch Mechanisms for Cantonese-English Neural Machine Translation
Kung Yin Hong, Lifeng Han, Riza Batista-Navarro +1
This paper investigates the development and evaluation of machine translation models from Cantonese to English, where we propose a novel approach to tackle low-resource language tr…