Papers by Zhongliang Yang
Towards Modern Topic Models: A Survey of Taxonomies and Paradigm Shifts from Algorithm-Centric to LLM-Centered Topic Analysis (2026.findings-acl)
Copied to clipboard
| Challenge: | Topic modeling (TM) is a classic unsupervised learning task in the field of natural language processing. |
| Approach: | They propose a new taxonomy that emphasizes the role of LLMs and the design of end-to-end workflows. |
| Outcome: | The proposed taxonomy emphasizes the role of LLMs and the design of end-to-end workflows. |
Provably Secure Generative Linguistic Steganography (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods of linguistic steganography generate high-security stegotext with statistical differences between the conditional probability distributions of stegot and natural text, which brings about security risks. |
| Approach: | They propose a method which embeds secret information by Adaptive Dynamic Grouping of tokens according to their probability given by an off-the-shelf language model. |
| Outcome: | The proposed method generates steganographic text with perfect security . it is based on three public corpora and proves its security based upon mathematical tests . |
Semantic Contribution-Aware Adaptive Retrieval for Black-Box Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to retrieval-agmented generation fail to generalize effectively in black-box scenarios. |
| Approach: | They propose a framework that leverages the semantic importance of words to dynamically adjust retrieval thresholds and filter information. |
| Outcome: | The proposed framework achieves the highest score on four long-form, knowledge-intensive generation datasets. |
ReSee: Responding through Seeing Fine-grained Visual Knowledge in Open-domain Dialogue (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing multimodal dialogue systems are limited by the scale and quality of available datasets or the coarse concept of visual knowledge. |
| Approach: | They propose to explicitly split visual knowledge into finer granularity and turn-level . they propose a framework to add visual representation into vanilla dialogue models . |
| Outcome: | The proposed framework outperforms state-of-the-art methods on automatic and human evaluations. |
AgentMark: Utility-Preserving Behavioral Watermarking for Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have improved text generation and reasoning. |
| Approach: | They propose a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility. |
| Outcome: | The proposed framework embeds multi-bit provenance into planning decisions while preserving utility. |