Papers by Chang Shu
All Roads Lead to Rome: Graph-Based Confidence Estimation for Large Language Model Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for confidence estimation are primarily designed for factual QA tasks and fail to generalize to reasoning tasks. |
| Approach: | They propose a set of training-free, graph-based confidence estimation methods tailored to reasoning tasks that exploit graph properties such as centrality, path convergence, and path weighting. |
| Outcome: | The proposed methods improve confidence estimation and performance on two downstream tasks. |
Early Rumour Detection (N19-1)
Copied to clipboard
| Challenge: | Existing studies on rumour detection are concerned with timing, but few are interested in how early we can detect them. |
| Approach: | They propose a method that integrates reinforcement learning to learn the minimum number of posts required before classifying an event as a rumour. |
| Outcome: | The proposed model detects rumours earlier than state-of-the-art systems while maintaining comparable accuracy. |
Logic-Consistency Text Generation from Semantic Parses (2021.findings-acl)
Copied to clipboard
| Challenge: | Text generation from semantic parses is challenging due to the complexity of the inner logic and the lack of automatic evaluation metrics for logic consistency. |
| Approach: | They propose a framework for logic consistent text generation from semantic parses that employs iterative training procedures and quality control. |
| Outcome: | The proposed framework enhances logic consistency and human evaluation on two benchmark datasets. |
How Furiously Can Colorless Green Ideas Sleep? Sentence Acceptability in Context (2020.tacl-1)
Copied to clipboard
| Challenge: | a recent study shows that context affects our perception of sentence acceptability, but few studies investigate how it affects language models. |
| Approach: | They compare acceptability ratings of sentences judged in isolation with a relevant context and with an irrelevant context. |
| Outcome: | The proposed model achieves state-of-the-art for unsupervised acceptability prediction. |
Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective (2023.eacl-main)
Copied to clipboard
Zijian Zhang, Chang Shu, Ya Xiao, Yuan Shen, Di Zhu, Youxin Chen, Jing Xiao, Jey Han Lau, Qian Zhang, Zheng Lu
| Challenge: | Recent VSE models combine simple pooling methods with hard triplet loss to improve performance. |
| Approach: | They propose an adaptive pooling strategy that allows the model to learn how to aggregate features through a combination of simple pooling methods. |
| Outcome: | The proposed strategy outperforms current state-of-the-art systems on image-to-text and text-toimage retrieval. |
POSQA: Probe the World Models of LLMs with Size Comparisons (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Embodied language comprehension emphasizes that language understanding is not only mental processing in the brain but also involves interactions with the physical and social environment. |
| Approach: | They propose to use a physical object size question to examine the extremity of large language models to test their embodied comprehension. |
| Outcome: | The proposed dataset shows that even the largest LLMs perform poorly under the zero-shot setting. |
Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks of social language are lacking for large language models. |
| Approach: | They propose a new benchmark that measures how well large language models understand social language by grouping 58 tasks into five categories: humor & sarcasm, offensiveness, sentiment & emotion, and trustworthiness. |
| Outcome: | The proposed model performs well at 58 tasks that are divided into five categories: humor & sarcasm, offensiveness, sentiment & emotion, and trustworthiness. |