Papers by Tianshu Zhang
ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search (2025.acl-long)
Copied to clipboard
Yize Zhang, Tianshu Wang, Sirui Chen, Kun Wang, Xingyu Zeng, Hongyu Lin, Xianpei Han, Le Sun, Chaochao Lu
| Challenge: | Large language models (LLMs) have impressive capabilities but their application in open-ended, knowledge-intensive, complex reasoning scenarios is limited. |
| Approach: | They propose a framework that integrates risk assessment of intermediate reasoning states with dynamic retrieval-augmented generation within a Monte Carlo tree search paradigm. |
| Outcome: | The proposed framework outperforms the state-of-the-art KAR methods by up to 23.10% and the latest RAG-equipped large reasoning models by upto 25.37%. |
Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis (2023.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal Sentiment Analysis (MSA) is effective when using rich information from multiple sources, but the potential sentiment-irrelevant information across modalities may hinder the performance from being further improved. |
| Approach: | They propose an Adaptive Language-guided Multimodal Transformer (ALMT) that learns an irrelevance/conflict-suppressing representation from visual and audio features under guidance of language features at different scales. |
| Outcome: | The proposed model achieves state-of-the-art on several popular datasets and an abundance of ablation shows the effectiveness of the proposed model. |
AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search (2026.findings-acl)
Copied to clipboard
| Challenge: | Experimental evaluation shows that AOT* achieves competitive solve rates using 3-5 fewer iterations than existing LLM-based approaches. |
| Approach: | They propose a framework that integrates LLM-generated chemical synthesis pathways with systematic AND-OR tree search. |
| Outcome: | Experimental results show that AOT* improves search efficiency and solves faster than existing approaches. |
Training Language Model to Critique for Better Refinement (2025.findings-acl)
Copied to clipboard
Tianshu Yu, Chao Xiang, Mingchuan Yang, Pei Ke, Bosi Wen, Cunxiang Wang, Jiale Cheng, Li Zhang, Xinyu Mu, Chuxiong Sun, Minlie Huang
| Challenge: | Large language models (LLMs) have remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks. |
| Approach: | They propose a framework to train critic models using refinement signals to generate feedback loops where critiques guide the model in refining its responses. |
| Outcome: | The proposed framework outperforms traditional methods and open-source models in terms of critique quality and refinement outcomes. |
Federated Learning for Semantic Parsing: Task Formulation, Evaluation Setup, New Algorithms (2023.acl-long)
Copied to clipboard
| Challenge: | Neural semantic parsers have achieved remarkable performance in recent years, but they are data-hungry and require annotators to have intimate knowledge of formal programs. |
| Approach: | They propose a task where multiple clients collaboratively train one global model without sharing their semantic parsing data. |
| Outcome: | The proposed model improves performance on three widely adopted FL algorithms (FedAvg, FedOPT and FedProx) and clients with smaller datasets enjoy faster performance. |
ReKG-MCTS: Reinforcing LLM Reasoning on Knowledge Graphs via Training-Free Monte Carlo Tree Search (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to combining knowledge graphs with large language models face limitations in path exploration strategies or excessive computational overhead. |
| Approach: | They propose a training-free framework that synergizes Monte Carlo Tree Search with LLM capabilities to enable dynamic reasoning over KGs. |
| Outcome: | The proposed framework outperforms existing training-free methods and achieves competitive performance compared to fine-tuned baselines. |
Exploring Chain of Thought Style Prompting for Text-to-SQL (2023.emnlp-main)
Copied to clipboard
| Challenge: | In-context learning with large language models (LLMs) has recently caught increasing attention due to its superior few-shot performance on various tasks. |
| Approach: | They propose a new chain of thought prompting method that enhances LLMs’ reasoning ability through chain of thinking prompting, including the original chain-of-thought prompting and least-to-most prompting. |
| Outcome: | The proposed method brings 5.2 and 6.5 point absolute gains on the Spider development set and the Spider Realistic set, respectively, compared to the standard prompting method without reasoning steps; 2.4 and 1.5 point absolute gain, versus the least-to-most prompting. |
TableLlama: Towards Open Large Generalist Models for Tables (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for interpreting, augmenting, and querying semi-structured tables require pretraining on tables or special model architecture design. |
| Approach: | They construct a dataset with a variety of tables and tasks for instruction tuning and evaluating LLMs. |
| Outcome: | The proposed model achieves comparable or better performance on 7 out of 8 in-domain tasks compared with the base model on 6 out-of-domain datasets. |