Papers by Ivor Tsang
Safety Sidecar: Reflection-Driven Runtime Control for Safer Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety controls fail to provide runtime intervention or cross-architecture portability for autonomous LLM agents. |
| Approach: | They propose a model-agnostic, plug-and-play module to provide arbitrary agent safety control and auditability. |
| Outcome: | The proposed module improves the secure-solution rate by 2.9–11.2 percentage points . it adds only 3.2s to end-to-end latency and a negligible average cost of 5.37 10-4 per scenario . |
DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition (2022.findings-acl)
Copied to clipboard
| Challenge: | Dialog sentiment classification (DSC) and dialog act recognition (DAR) aims to predict the sentiment label and act label for each utterance in a dialog. |
| Approach: | They propose a framework which integrates prediction-level interactions other than semantics-level ones into dialog understanding and dual-task reasoning by integrating temporal relations into the model. |
| Outcome: | The proposed model outperforms existing models by large margins while costing less training time and requiring less computation resource. |
DC-Instruct: An Effective Framework for Generative Multi-intent Spoken Language Understanding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing prompt learning frameworks lack explicit modeling of dual-task dependencies and oversight of task-specific semantic differences among utterances. |
| Approach: | They propose a generative framework based on Dual-task Inter-dependent Instructions (DII) and Supervised Contrastive Instructions that leverages utterance semantics differences by guiding LLMs to determine whether a pair of utterrances share the same or similar labels. |
| Outcome: | The proposed framework outperforms existing models and state-of-the-art methods on public benchmark datasets and shows that it improves SLU reasoning. |
Causal Intervention for Abstractive Related Work Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models ignore the inherent causality during related work generation, leading to spurious correlations which downgrade the models’ generation quality and generalizability. |
| Approach: | They propose a Causal Intervention Module for Related Work Generation (CaM) that captures causal relationships in related work generation and implements causal interventions to mitigate the negative impact of spurious correlations. |
| Outcome: | The proposed framework improves the quality and coherence of generated related work by capturing causalities in the generation process. |
From Language to Driving: A Dual-Loop SLM-Enhanced Framework for Multi-Planner Scheduling via a Domain-Specific Language (2026.acl-long)
Copied to clipboard
Jiawei Liu, Xun Gong, Muli Yang, Xingrui Yu, Fen Fang, Xulei Yang, Ivor Tsang, Yunfeng hu, Hong Chen, Qing Guo
| Challenge: | Recent large language model-based AD research offers new avenues to address this challenge. |
| Approach: | They propose a small language model (SLM) for high-level semantic reasoning and schedule generation, while an inner loop performs low-level, high-frequency schedule execution and vehicle control. |
| Outcome: | The proposed framework improves instruction completion rates while maintaining high safety and compliance relative to multiple baselines. |
Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent joint multiple intent detection and slot filling models ignore the dependencies among labels and label embeddings. |
| Approach: | They propose to construct a Heterogeneous Label Graph (HLG) containing two kinds of topologies and a novel model termed ReLa-Net which captures beneficial correlations among the labels from HLG. |
| Outcome: | The proposed model outperforms the previous model by over 20% on MixATIS dataset. |
Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing graph-based models only model the unidirectional guidance from intent to slot, which limits the performance. |
| Approach: | They propose a graph-based model that leverages the correlations between intent and slot to achieve mutual guidances between the two tasks. |
| Outcome: | The proposed model outperforms existing models by 19.3% in overall accuracy. |