Bo Ni
Author directory2026
Ensemble Privacy Defense for Knowledge-Intensive LLMs against Membership Inference Attacks
Haowei Fu | Bo Ni | Han Xu | Kunpeng Liu | Dan Lin | Tyler Derr
Findings of the Association for Computational Linguistics: EACL 2026
Haowei Fu | Bo Ni | Han Xu | Kunpeng Liu | Dan Lin | Tyler Derr
Findings of the Association for Computational Linguistics: EACL 2026
Retrieval-Augmented Generation (RAG) and Supervised Finetuning (SFT) have become the predominant paradigms for equipping Large Language Models (LLMs) with external knowledge for diverse, knowledge-intensive tasks. However, while such knowledge injection improves performance, it also exposes new attack surfaces. Membership Inference Attacks (MIAs), which aim to determine whether a given data sample was included in a model’s training set, pose serious threats to privacy and trust in sensitive domains. To this end, we first systematically evaluate the vulnerability of RAG- and SFT-based LLMs to various MIAs. Then, to address the privacy risk, we further introduce a novel, model-agnostic defense framework, Ensemble Privacy Defense (EPD), which aggregates and evaluates the outputs of a knowledge-injected LLM, a base LLM, and a dedicated judge model to enhance resistance against MIAs. Comprehensive experiments show that, on average, EPD reduces MIA success by up to 27.8% for SFT and 526.3% for RAG compared to inference-time baseline, while maintaining answer quality.
Risk-Controlled Event-Driven Cascading Updates for Knowledge Graph Consistency Restoration
Bo Ni | Qinwen Ge | Haowei Fu | Ryan A. Rossi | Xiaorui Liu | Jiejun Xu | Tyler Derr
Findings of the Association for Computational Linguistics: ACL 2026
Bo Ni | Qinwen Ge | Haowei Fu | Ryan A. Rossi | Xiaorui Liu | Jiejun Xu | Tyler Derr
Findings of the Association for Computational Linguistics: ACL 2026
Knowledge Graphs (KGs) provide structured and interpretable representations of real-world entities and relations. While dynamic KGs attempt to capture real-time changes, they typically treat updates as independent facts. This overlooks a critical challenge: a factual, localized update can contradict and invalidate previously correct knowledge, requiring revisions beyond the localized update to maintain KG consistency. Many of these inconsistencies arise from events whose effects propagate through relational dependencies, necessitating coordinated multi-hop reasoning rather than isolated changes. To address this, we introduce a model-agnostic framework for cascading KG update identification that leverages conformal prediction to provide reliable uncertainty guarantees over the cascade as a whole, accounting for dependencies among multi-hop update candidates. Building on this foundation, we further develop a graph-based KG update scoring framework that integrates large language models (LLMs) to enrich event representations with world knowledge. Experiments on two newly constructed real-world datasets, designed to reflect scenarios where events necessitate coordinated multi-hop updates, demonstrate that our framework establishes a strong baseline while offering calibrated confidence estimates, providing an effective solution for event-driven KG consistency restoration.
A Survey on LLM-based Conversational User Simulation
Bo Ni | Yu Wang | Leyao Wang | Branislav Kveton | Franck Dernoncourt | Yu Xia | Hongjie Chen | Reuben Luera | Samyadeep Basu | Subhojyoti Mukherjee | Puneet Mathur | Nesreen K. Ahmed | Junda Wu | Li Li | Huixin Zhang | Ruiyi Zhang | Tong Yu | Sungchul Kim | Jiuxiang Gu | Zhengzhong Tu | Alexa Siu | Zichao Wang | Seunghyun Yoon | Nedim Lipka | Namyong Park | Zihao Lin | Trung Bui | Yue Zhao | Tyler Derr | Ryan A. Rossi
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Bo Ni | Yu Wang | Leyao Wang | Branislav Kveton | Franck Dernoncourt | Yu Xia | Hongjie Chen | Reuben Luera | Samyadeep Basu | Subhojyoti Mukherjee | Puneet Mathur | Nesreen K. Ahmed | Junda Wu | Li Li | Huixin Zhang | Ruiyi Zhang | Tong Yu | Sungchul Kim | Jiuxiang Gu | Zhengzhong Tu | Alexa Siu | Zichao Wang | Seunghyun Yoon | Nedim Lipka | Namyong Park | Zihao Lin | Trung Bui | Yue Zhao | Tyler Derr | Ryan A. Rossi
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
User simulation has long played a vital role in computer science due to its potential to support a wide range of applications. Language, as the primary medium of human communication, forms the foundation of social interaction and behavior. Consequently, simulating conversational behavior has become a key area of study. Recent advancements in large language models (LLMs) have significantly catalyzed progress in this domain by enabling high-fidelity generation of synthetic user conversation. In this paper, we survey recent advancements in LLM-based conversational user simulation. We introduce a novel taxonomy covering user granularity and simulation objectives. Additionally, we systematically analyze core techniques and evaluation methodologies. We aim to keep the research community informed of the latest advancements in conversational user simulation and to further facilitate future research by identifying open challenges and organizing existing work under a unified framework.
Reasoning-Based Personalized Generation for Sparse Users
Bo Ni | Branislav Kveton | Samyadeep Basu | Subhojyoti Mukherjee | Leyao Wang | Franck Dernoncourt | Sungchul Kim | Seunghyun Yoon | Zichao Wang | Ruiyi Zhang | Puneet Mathur | Jihyung Kil | Jiuxiang Gu | Nedim Lipka | Yu Wang | Ryan A. Rossi | Tyler Derr
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Bo Ni | Branislav Kveton | Samyadeep Basu | Subhojyoti Mukherjee | Leyao Wang | Franck Dernoncourt | Sungchul Kim | Seunghyun Yoon | Zichao Wang | Ruiyi Zhang | Puneet Mathur | Jihyung Kil | Jiuxiang Gu | Nedim Lipka | Yu Wang | Ryan A. Rossi | Tyler Derr
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, real-world users usually possess sparse interaction histories with limited personal context, such as cold-start users in social platforms and newly registered customers in online E-commerce platforms, compromising the LLM-based personalized generation. To address this challenge, we introduce GraSPer (Graph-based Sparse Personalized Reasoning), a novel framework for enhancing personalized text generation under sparse context. GraSPer first augments user context by predicting items that the user would likely interact with in the future. With reasoning alignment, it then generates texts for these interactions to enrich the augmented context. In the end, it generates personalized outputs conditioned on both the real and synthetic histories, ensuring alignment with user style and preferences. Extensive experiments on three benchmark personalized generation datasets show that GraSPer achieves significant performance gain, substantially improving personalization in sparse user context settings.
Search
Co-authors
- Tyler Derr 4
- Ryan A. Rossi 3
- Samyadeep Basu 2
- Franck Dernoncourt 2
- Haowei Fu 2
- Jiuxiang Gu 2
- Sungchul Kim 2
- Branislav Kveton 2
- Nedim Lipka 2
- Puneet Mathur 2
- Subhojyoti Mukherjee 2
- Leyao Wang 2
- Yu Wang 2
- Zichao Wang 2
- Seunghyun Yoon 2
- Ruiyi Zhang 2
- Nesreen K. Ahmed 1
- Trung Bui 1
- Hongjie Chen 1
- Qinwen Ge 1
- Jihyung Kil 1
- Li Li 1
- Dan Lin 1
- Zihao Lin 1
- Kunpeng Liu 1
- Xiaorui Liu 1
- Reuben Luera 1
- Namyong Park 1
- Alexa Siu 1
- Zhengzhong Tu 1
- Junda Wu 1
- Yu Xia 1
- Han Xu 1
- Jiejun Xu 1
- Tong Yu 1
- Huixin Zhang 1
- Yue Zhao 1