Papers by Cen Zhao
Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment. |
| Approach: | They propose a framework that trains models to engage in explicit safe reasoning before response . they propose RATIONAL, which allows models to reject harmful prompts while providing meaningful and context-aware responses. |
| Outcome: | The proposed framework fine-tunes models to reason about query intent, ethics, and potential harm. |
LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing long-context Large Language Models (LLMs) struggle with the “lost in the middle” issue. |
| Approach: | They propose a general, dual-perspective, and robust LLM-based RAG system paradigm for LCQA to enhance RAG’s understanding of complex long-context knowledge. |
| Outcome: | The proposed system outperforms long-context LLMs, advanced RAG, and vanilla RAG on three multi-hop datasets. |
Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Using a mixtral-87B model, we reduce the time it takes to generate concise notes during conversations, and reduce the amount of time spent on manual review. |
| Approach: | They propose a system that combines a Mixtral-87B model for continuous note generation with a DeBERTa-based classifier to filter trivial content. |
| Outcome: | The proposed system achieved a 3% reduction in case handling time compared to bulk summarization, and high agent satisfaction ratings from surveys. |
Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support (2025.emnlp-industry)
Copied to clipboard
Cen Zhao, Tiantian Zhang, Hanchen Su, Yufeng Zhang, Shaowei Su, Mingzhi Xu, Yu Liu, Wei Han, Jeremy Werner, Claire Na Cheng, Yashar Mehdad
| Challenge: | Existing offline approaches to improve an LLM-based customer support system rely on batch annotations. |
| Approach: | They propose an agent-in-the-loop framework that integrates four key types of annotations directly into live customer operations: (1) pairwise response preferences, (2) agent adoption and rationales, (3) knowledge relevance checks, and (4) identification of missing knowledge. |
| Outcome: | The proposed framework reduces retraining cycles from months to weeks by integrating four key types of annotations directly into live customer operations. |
Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training (2025.findings-acl)
Copied to clipboard
Yihang Yao, Zhepeng Cen, Miao Li, William Han, Yuyou Zhang, Emerson Liu, Zuxin Liu, Chuang Gan, Ding Zhao
| Challenge: | Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks. |
| Approach: | They propose a data-centric approach that enhances LLMs’ awareness of symmetry in query variations and propose syMmetry-ENhanceD (MEND) data augmentation. |
| Outcome: | Extensive experiments on logical and arithmetic reasoning tasks show that the proposed approach improves model robustness at the knowledge extraction stage through query augmentation. |