Papers by Baoyuan Wang
MorphMark: Flexible Adaptive Watermarking for Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for tracing text origins struggle with a watermark effectiveness dilemma . weaker watermarks preserve text quality, while stronger ones enhance effectiveness . |
| Approach: | They propose a method that adjusts watermark strength in response to changes in a key factor . they first formalize the problem within a multi-objective trade-off analysis framework . |
| Outcome: | The proposed method improves watermark effectiveness but reduces text quality . the proposed method prioritizes flexibility and time and space efficiency . |
Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding (2025.emnlp-main)
Copied to clipboard
| Challenge: | In-Context Learning (ICL) is a key method in prompt engineering, but its long retrieved contexts and limited token throughput will slow reasoning speeds. |
| Approach: | They propose a method that leverages the overlap between context and model output to generate drafts from the context. |
| Outcome: | The proposed method achieves the highest mean speedup on Vicuna-7B, Llama2-7B-Chat, and Llma3-8B-Instruct tasks. |
DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Chain-of-Thought prompting has improved the reasoning capabilities of Large Language Models (LLMs) but it is ineffective or detrimental to the performance on reasoning tasks in Smaller Language Model (SLMs) with less than 10 billion parameters. |
| Approach: | They propose a Dialogue-guided Chain-of-Thought method to improve the reasoning capabilities of Large Language Models (LLMs) by generating intermediate reasoning steps in a dialogue format to guide the model to the final answer. |
| Outcome: | The proposed method can achieve significant performance gains over state-of-the-art competitors on four arithmetic reasoning datasets. |
Natural Response Generation for Chinese Reading Comprehension (2023.findings-emnlp)
Copied to clipboard
| Challenge: | MRC models trained on labeled answers are limited in generating human-like responses in real QA scenarios. |
| Approach: | They construct a dataset called Penguin to promote machine reading comprehension . they use 200k training data with fluent, well-informed responses to train models . |
| Outcome: | The proposed dataset is the first benchmark towards natural response generation in Chinese MRC on a relatively large scale. |
LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming (2023.acl-long)
Copied to clipboard
| Challenge: | a recent study shows that open-domain dialogue systems are not able to perform well in fast-growing scenarios such as live streaming due to the domain gap between online-post constructed data and those required in downstream conversational tasks. |
| Approach: | They propose to train a conversational agent based on large social media datasets with multiple domains to improve response in live streaming scenarios. |
| Outcome: | The proposed model improves response modeling and addressee recognition in live open-domain scenarios. |
Robust and Minimally Invasive Watermarking for EaaS (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing watermarking methods use a target embedding to create watermarks, but this method results in each embeddable having the same component, making it difficult to remove the watermark. |
| Approach: | They propose to use embedding watermarks to protect EaaS from model extraction attacks . eaas is vulnerable to model extraction, highlighting the need for copyright protection . |
| Outcome: | The proposed method can watermark embeddings against model extraction attacks without sacrificing the quality of the embeddables. |
Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension (2023.findings-emnlp)
Copied to clipboard
Nuo Chen, Hongguang Li, Junqing He, Yinan Bao, Xinshi Lin, Qi Yang, Jianfeng Liu, Ruyi Gan, Jiaxing Zhang, Baoyuan Wang, Jia Li
| Challenge: | Existing benchmarks for conversational machine reading comprehension are inconsistent with real scenarios. |
| Approach: | They propose to use a Chinese CMRC benchmark to evaluate model's generalization ability towards diverse domains by using zero-shot/few-shot settings. |
| Outcome: | The proposed benchmarks are based on 831 hot-topic driven conversations with 4,742 turns and cover 33 domains. |
Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations (2025.coling-main)
Copied to clipboard
| Challenge: | Existing retrieval-based methods for long-term conversations face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. |
| Approach: | They propose a framework that eschews traditional retrieval modules and memory databases and adopts a “One-for-All” approach to manage memory generation, compression, and response generation. |
| Outcome: | The proposed framework produces more nuanced and human-like experiences than retrieval-based methods. |
SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive capabilities across various fields, but their widespread use is facing a severe and realistic challenge, which is their high demand for GPU memory. |
| Approach: | They propose a KV cache reduction method which balances both shallow and deep layers by using an attention weight based eviction method and a codebook based replacement approach. |
| Outcome: | The proposed method reduces the KV cache for shallower layers while preserving similar or even better model performance. |
Towards Objectively Benchmarking Social Intelligence of Language Agents at the Action Level (2024.findings-acl)
Copied to clipboard
| Challenge: | evaluative findings highlight that the STSS benchmark is challenging for state-of-the-art language agents. |
| Approach: | They propose a social task in sandbox simulation benchmark that assesses language agents objectively at the action level by scrutinizing goal achievements within the multi-agent simulation. |
| Outcome: | The proposed social task-in-sandbox simulation is a language-level benchmark . the proposed benchmark effectively discriminates between distinct language agents . |
Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification (2023.acl-long)
Copied to clipboard
| Challenge: | Existing work on the hierarchical text classification problem is limited due to the complexity of label hierarchy and intensive labeling cost. |
| Approach: | They propose a path-based few-shot setting and a strict path-basic evaluation metric to further explore few- shot HTC tasks. |
| Outcome: | The proposed framework outperforms those who inject hierarchy through graph encoders on three popular HTC datasets under the few-shot setting. |
Triplet-Free Knowledge-Guided Response Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Prior work focused on constructing ”latent” knowledge and learning how to ground it based on pseudo triplets. |
| Approach: | They propose to pretrain a response language model to measure relevance and consistency between any context and response and use search engines to collect top-ranked passages to serve as guiding knowledge without explicitly optimizing the ‘‘best’ latent knowledge. |
| Outcome: | The proposed model pretrains a response language model to measure relevance and consistency between any context and response, then uses search engines to collect the top-ranked passages to serve as the guiding knowledge without explicitly optimizing the ‘‘best’ latent knowledge. |