Papers by Boyuan Zheng
Multilingual Coreference Resolution in Multiparty Dialogue (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing datasets for entity coreference resolution are limited to English and other languages are rare. |
| Approach: | They propose to use TV transcripts to create multilingual multiparty coreference datasets that leverage existing subtitles in Chinese and Farsi. |
| Outcome: | The proposed dataset re-annotates for coreference on TV transcripts and then leverages existing subtitle translations to create a multilingual corpus. |
Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have shown that the effective use of contextual information between sentences can achieve better performance in document-level machine translation. |
| Approach: | They propose a recurrent memory unit to the Transformer to support the information exchange between the sentence and previous context. |
| Outcome: | The proposed model outperforms the previous work on TED and News by 0.91 s-BLEU and 1.49 d-BLUE on average. |
WebOlympus: An Open Platform for Web Agents on Live Websites (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Web agents are emerging as powerful tools for automating tasks in cyberspace . however, there is a lack of standardized and user-friendly tools for research and development . |
| Approach: | They propose an open platform for web agents operating on live websites with a Chrome extension and a safety monitor module to ensure their trustworthiness. |
| Outcome: | WebOlympus is an open platform for web agents operating on live websites. |
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)
Copied to clipboard
Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang
| Challenge: | Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours. |
| Approach: | They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs . |
| Outcome: | The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models. |
Flatness-Aware Prompt Selection Improves Accuracy and Sample Efficiency (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Manually "engineering" prompts for large language models can be laborious and time-intensive. |
| Approach: | They propose a new metric to quantify the expected utility of a language prompt. |
| Outcome: | The proposed metric outperforms previous prompt selection metrics with 10% increase in Pearson correlation across 6 classification benchmarks and the prompt selected by the proposed meter gains 5% higher accuracy than previous metrics. |
Look and Think: Efficient Multimodal Reasoning via Modality-Decoupled Compression (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal large language models have strong performance on visual question answering benchmarks . however, their inference efficiency is severely constrained by the rapidly growing context . |
| Approach: | They propose a modality-decoupled compression method that enables efficient multimodal inference . they propose to evict visual tokens whenever visual grounding is unnecessary . |
| Outcome: | The proposed method reduces the average context length by up to 57% while maintaining comparable performance to the standard MLLM baseline. |
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts (2024.findings-acl)
Copied to clipboard
Lingfeng Shen, Weiting Tan, Sihao Chen, Yunmo Chen, Jingyu Zhang, Haoran Xu, Boyuan Zheng, Philipp Koehn, Daniel Khashabi
| Challenge: | Recent studies show that malicious prompt instructions could solicit objectionable content from LLMs. |
| Approach: | They compare how state-of-the-art LLMs respond to malicious prompts in different languages . they find that LLM's generate unsafe responses more often when a prompt is written in a lower-resource language . |
| Outcome: | The proposed model can generate unsafe responses more often when a malicious prompt is written in a lower-resource language, and less irrelevant responses when written in lower-source languages. |
An Empirical Study on Finding Spans (2022.emnlp-main)
Copied to clipboard
| Challenge: | Various information extraction tasks require a span finding component, which either directly yields the output or serves as an essential component of downstream linking. |
| Approach: | They propose methods for span finding, the selection of consecutive tokens in text for some downstream tasks. |
| Outcome: | The proposed methods perform better on masked language models and pre-trained encoders than on encoder-decoder models. |