Papers by Jinggui Liang
Synergizing Large Language Models and Pre-Trained Smaller Models for Conversational Intent Discovery (2024.findings-acl)
Copied to clipboard
| Challenge: | Current attempts at CID rely on pretrained Small Language Models (SLMs) this lacks the ability to label new intents and is a challenge for small language models. |
| Approach: | They propose to combine Large Language Models (LLMs) with pre-trained SLMs for CID to enhance the semantic comprehension of LLMs. |
| Outcome: | The proposed approach improves the semantic comprehension of LLMs and the operational agility of SLMs by realigning existing descriptors within the SLM’s feature space to correct cluster distortion and promote robust learning of representations. |
A Survey of Ontology Expansion for Conversational Understanding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Current methods for conversational understanding rely on static ontologies, limiting their ability to handle new and unforeseen user needs. |
| Approach: | They propose to review the state-of-the-art techniques in OnExp for conversational understanding and highlight emerging frontiers . they categorize existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp. |
| Outcome: | The proposed methods highlight several emerging frontiers in OnExp to improve agent performance in real-world scenarios and discuss their corresponding challenges. |
Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing retrieval-augmented generation paradigms rely on semantic similarity to retrieve historical dialogues that are surface analogous but therapeutically incongruent. |
| Approach: | They propose to use appraisal-guided reasoning chains to generate appraisal-based reasoning chains and apply a dual-signal verification mechanism to verify and correct them. |
| Outcome: | Extensive experiments on two ESC benchmarks show that the proposed model significantly outperforms state-of-the-art models. |
Colloquial Singaporean English Style Transfer with Fine-Grained Explainable Control (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for style transfer between Singlish and Standard English lack explainability and fine-grained control. |
| Approach: | They propose a multi-agent framework where large language models act as expert agents for each linguistic aspect. |
| Outcome: | The proposed model enables precise, interpretable transformations, advancing explainability in NLP for Singlish. |
LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing security guardrails built from static datasets ignore each model’s unique safety profile and often force trade-offs between safety and utility. |
| Approach: | They propose a framework for learning model-specific guardrails tailored to each LLM’s vulnerabilities. |
| Outcome: | The proposed framework significantly outperforms baseline guardrails on multiple real-world LLMs, achieving superior robustness, adaptability, and generalization. |
Actively Learn from LLMs with Uncertainty Propagation for Generalized Category Discovery (2024.naacl-long)
Copied to clipboard
| Challenge: | Generalized category discovery (GCD) is a crucial task in open-world computing, where new categories frequently emerge, necessitating models that can adapt and learn continually. |
| Approach: | They propose to integrate the feedback from LLMs into an active learning paradigm to simplify the labeling task and minimize the spread of inaccurate feedback. |
| Outcome: | The proposed approach significantly improves baseline models at a nominal average cost. |
ClusterPrompt: Cluster Semantic Enhanced Prompt Learning for New Intent Discovery (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for identifying new intent categories focus on relations between utterances and clusters, while neglecting the usage of semantics. |
| Approach: | They propose a method that leverages contrastive learning and label semantic alignment to learn meaningful representations of intent clusters. |
| Outcome: | The proposed method outperforms existing methods and suggests meaningful intent labels. |
IntentionFrame: A Semi-Structured, Multi-Aspect Framework for Fine-Grained Conversational Intention Understanding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for understanding user intentions in multi-turn dialogues fail to capture conversational complexity. |
| Approach: | They propose a semi-structured framework which organizes conversational intents into four interrelated aspects: situation, emotion, action, and knowledge. |
| Outcome: | The proposed framework retains interpretability and provides a rich context to accurately parse and respond to nuanced user inputs. |