papers

Publications (19)

cs.CL2023

Can ChatGPT-like Generative Models Guarantee Factual Accuracy? On the Mistakes of New Generation Search Engines

Ruochen Zhao, Xingxuan Li, Yew Ken Chia +2

Although large conversational AI models such as OpenAI's ChatGPT have demonstrated great potential, we question whether such models can guarantee factual accuracy. Recently, techno…

cs.AI2024

Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents

Long Li, Weiwen Xu, Jiayan Guo +11

Effective research ideation is a critical step for scientific research. However, the exponential increase in scientific literature makes it challenging for researchers to stay curr…

cs.CL2024

Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks

Xingxuan Li, Weiwen Xu, Ruochen Zhao +3

State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harn…

cs.CL2024

Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges

Bosheng Ding, Chengwei Qin, Ruochen Zhao +7

In the rapidly evolving field of large language models (LLMs), data augmentation (DA) has emerged as a pivotal technique for enhancing model performance by diversifying training ex…

cs.CL2023

Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework

Ruochen Zhao, Xingxuan Li, Shafiq Joty +2

As large language models (LLMs) have become the norm in NLP, demonstrating good performance in generation and reasoning tasks, one of its most fatal disadvantages is the lack of fa…

cs.CL2023

Explaining Language Models' Predictions with High-Impact Concepts

Ruochen Zhao, Shafiq Joty, Yongjie Wang +1

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the com…

cs.CL2025

A Comprehensive Survey of Contamination Detection Methods in Large Language Models

Mathieu Ravaut, Bosheng Ding, Fangkai Jiao +6

With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming criti…

cs.CL2026

BranPO: Scalable Contrastive Branch Sampling for Long-Horizon Agentic Reinforcement Learning

Yubao Zhao, Weiquan Huang, Sudong Wang +4

Agentic reinforcement learning enables large language models to perform multi-turn planning and tool use, but long-horizon training remains challenging under sparse trajectory-leve…

cs.AI2025

AgREE: Agentic Reasoning for Knowledge Graph Completion on Emerging Entities

Ruochen Zhao, Simone Conia, Eric Peng +2

Open-domain Knowledge Graph Completion (KGC) faces significant challenges in an ever-changing world, especially when considering the continual emergence of new entities in daily ne…

cs.CL2023

Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?

Chengwei Qin, Qian Li, Ruochen Zhao +1

Prompt tuning (PT) which only tunes the embeddings of an additional sequence of tokens per task, keeping the pre-trained language model (PLM) frozen, has shown remarkable performan…

cs.CL2023

Retrieving Multimodal Information for Augmented Generation: A Survey

Ruochen Zhao, Hailin Chen, Weishi Wang +8

As Large Language Models (LLMs) become popular, there emerged an important trend of using multimodality to augment the LLMs' generation ability, which enables LLMs to better intera…

cs.CL2023

Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications

Han Cheol Moon, Shafiq Joty, Ruochen Zhao +2

Large-scale pre-trained language models have shown outstanding performance in a variety of NLP tasks. However, they are also known to be significantly brittle against specifically…

cs.CL2024

Lifelong Event Detection with Embedding Space Separation and Compaction

Chengwei Qin, Ruirui Chen, Ruochen Zhao +2

To mitigate forgetting, existing lifelong event detection methods typically maintain a memory module and replay the stored memory data during the learning of a new task. However, t…

cs.AI2026

Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems

Hehai Lin, Yu Yan, Zixuan Wang +6

Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked…

cs.CL2026

DR-Arena: an Automated Evaluation Framework for Deep Research Agents

Yiwen Gao, Ruochen Zhao, Yang Deng +1

As Large Language Models (LLMs) increasingly operate as Deep Research (DR) Agents capable of autonomous investigation and information synthesis, reliable evaluation of their task p…

cs.CL2024

ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?

Hailin Chen, Fangkai Jiao, Xingxuan Li +5

Upon its release in late 2022, ChatGPT has brought a seismic shift in the entire landscape of AI, both in research and commerce. Through instruction-tuning a large language model (…

cs.CL2023

PromptSum: Parameter-Efficient Controllable Abstractive Summarization

Mathieu Ravaut, Hailin Chen, Ruochen Zhao +3

Prompt tuning (PT), a parameter-efficient technique that only tunes the additional prompt embeddings while keeping the backbone pre-trained language model (PLM) frozen, has shown p…

cs.CL2024

Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions

Ruochen Zhao, Wenxuan Zhang, Yew Ken Chia +3

As LLMs continuously evolve, there is an urgent need for a reliable evaluation method that delivers trustworthy results promptly. Currently, static benchmarks suffer from inflexibi…

cs.CL2024

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources

Xingxuan Li, Ruochen Zhao, Yew Ken Chia +4

We present chain-of-knowledge (CoK), a novel framework that augments large language models (LLMs) by dynamically incorporating grounding information from heterogeneous sources. It…