Papers by Shangsong Liang
MolRAG: Unlocking the Power of Large Language Models for Molecular Property Prediction (2025.acl-long)
Copied to clipboard
| Challenge: | Recent LLMs exhibit limited effectiveness on molecular property prediction task due to semantic gap between representations and natural language and lack of domain-specific knowledge. |
| Approach: | They propose a framework that integrates Chain-of-Thought reasoning for molecular property prediction. |
| Outcome: | The proposed framework outperforms pre-trained LLMs on four datasets and matches supervised methods. |
L4: Mutual Learning Helps Lifelong Language Learning (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing distillation methods rely on domain-specific teachers, limiting their ability to update in real-time and adapt to dynamic environments. |
| Approach: | They propose a framework that enables continuous mutual learning from task streams without relying on domain-specific teachers. |
| Outcome: | The proposed framework reduces catastrophic forgetting while improving performance on various benchmark datasets making it suitable for real-world, dynamic natural language processing (NLP) applications. |
Intrinsic Mutual Information as a Modulator for Preference Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for offline preference optimization involve additional hyperparameter tuning, resulting in substantial time overhead. |
| Approach: | They propose a lightweight framework for offline preference optimization that leverages hyperparameter modulation to decouple preference contributions. |
| Outcome: | The proposed framework achieves superior performance over existing methods while reducing training overhead by more than 15%. |
SAFARI: Cross-lingual Bias and Factuality Detection in News Media and News Articles (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a new corpus of news media and articles is developed to assess political bias and factuality in cross-lingual contexts . integrity and objectivity of news are crucial in an age of information sharing across cultural and language landscapes - a recent study shows . |
| Approach: | They propose a corpus of news media and articles for predicting political bias and factuality . they evaluate the cross-lingual ability of the models; however, they evaluate on English data . |
| Outcome: | The proposed corpus is unprecedented in its collection and evaluates on English data. |
MGM: Global Understanding of Audience Overlap Graphs for Predicting the Factuality and the Bias of News Media (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for profiling news media focus on textual features, causing them to overlook complex relationships between entities. |
| Approach: | They propose a framework for profiling news media from the lens of political bias and factuality. |
| Outcome: | The proposed framework improves existing models and improves them by integrating structural information from similar nodes. |
Revisiting Parameter-Efficient Tuning: Are We Really There Yet? (2022.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained language models (PLMs) are used as backbones to be combined with additional parameters and finetuned on downstream tasks in an end-to-end manner. |
| Approach: | They propose to use a fraction of parameters to tune pretrained language models (PLMs) this is the first comprehensive investigation into the training and evaluation of PETuning methods. |
| Outcome: | The proposed methods have been validated and tested with a rigorous evaluation protocol and have shown that they are unstable and inconsistent. |
Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches prioritize performance but overlook the balance between effectiveness and computational cost. |
| Approach: | They propose a plug-and-play framework that integrates with existing search strategies to improve LLM decision-making while maintaining efficiency. |
| Outcome: | The proposed framework reduces costs to 1/10 of the original search framework while maintaining effectiveness. |