Papers by Jiashuo Sun
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to generate reasoning programs that ignore the differences between facts treated all facts equally, leading to wrong punishment of programs that differed from the ground truth. |
| Approach: | They propose an optimized training framework for long-form numerical reasoning that incorporates a number-aware negative sampling strategy and consistency-based reinforcement learning to increase execution accuracy. |
| Outcome: | The proposed method improves the performance of long-form numerical reasoning on the FinQA and ConvFinQA leaderboards. |
Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning (2025.coling-main)
Copied to clipboard
| Challenge: | Large Vision-Language Models (LVLMs) have impressive capabilities in multi-modal context comprehension, but they still suffer from hallucination problems due to inconsistent outputs with the image content. |
| Approach: | They propose a training-free framework MVP to reduce hallucinations in Large Vision-Language Models . they propose multi-view information-seeking strategy to perceive the comprehensive information in the image . |
| Outcome: | The proposed framework reduces hallucinations in large vision-language models by combining multi-view multi-path reasoning with multi-vision multi-path reasoning. |
Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Chain-of-thought (CoT) prompting is a technique to enhance the reasoning abilities of Large language models (LLMs) however, the reasoning chains of demonstrations are observed to be prone to errors, which can lead to incorrect reasoning during inference. |
| Approach: | They propose an iterative bootstrapping technique to enhance the reasoning abilities of Large language models (LLMs) by generating a series of reasoning steps to obtain the answer, and using the reasoning chains as exemplars to demonstrate the task. |
| Outcome: | The proposed method improves the performance of Large language models (LLMs) on three reasoning tasks on ten datasets. |
SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on the text modality or are limited to specific tasks. |
| Approach: | They propose a framework to teach Large Vision-Language Models to selectively utilize retrieved information and improve their robustness against irrelevant or misleading references. |
| Outcome: | The proposed framework improves LVLMs’ ability to utilize retrieved multimodal references and their robustness against irrelevant or misleading information. |
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models (2024.naacl-long)
Copied to clipboard
Yi Luo, Zhenghao Lin, YuHao Zhang, Jiashuo Sun, Chen Lin, Chengjin Xu, Xiangdong Su, Yelong Shen, Jian Guo, Yeyun Gong
| Challenge: | Guide-Align is a guideline-oriented approach to augment the safety and quality of Large Language Models. |
| Approach: | They propose a guideline-oriented method to augment the safety and quality of large language models. |
| Outcome: | The proposed method outperforms existing methods on three benchmarks and shows significant improvements in security and quality. |