17 citations · 103 across the 53 of their papers we have counts for
53 papers
Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery
Tianyun Zhong, Wangyi Jiang, Wei Wang +15
Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured.…
MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
Ruoran Li, Xinghua Zhang, Haiyang Yu +7
Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introdu…
EvoRoute: Experience-Driven Self-Routing LLM Agent Systems
Guibin Zhang, Haiyang Yu, Kaiming Yang +4
Complex agentic AI systems, powered by a coordinated ensemble of Large Language Models (LLMs), tool and memory modules, have demonstrated remarkable capabilities on intricate, mult…
ExpSeek: Self-Triggered Experience Seeking for Web Agents
Wenyuan Zhang, Xinghua Zhang, Haiyang Yu +5
Experience intervention in web agents emerges as a promising technical paradigm, enhancing agent interaction capabilities by providing valuable insights from accumulated experience…
Understanding Generalization in Role-Playing Models via Information Theory
Yongqi Li, Hao Lang, Fei Huang +2
Role-playing models (RPMs) are widely used in real-world applications but underperform when deployed in the wild. This degradation can be attributed to distribution shifts, includi…
Selective Weak-to-Strong Generalization
Hao Lang, Fei Huang, Yongbin Li
Future superhuman models will surpass the ability of humans and humans will only be able to \textit{weakly} supervise superhuman models. To alleviate the issue of lacking high-qual…
EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models
Tao Zou, Xinghua Zhang, Haiyang Yu +3
With the development and widespread application of large language models (LLMs), the new paradigm of "Model as Product" is rapidly evolving, and demands higher capabilities to addr…
Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns
Xiang Li, Haiyang Yu, Xinghua Zhang +6
Process Reward Models (PRMs) are crucial in complex reasoning and problem-solving tasks (e.g., LLM agents with long-horizon decision-making) by verifying the correctness of each in…
Reverse Preference Optimization for Complex Instruction Following
Xiang Huang, Ting-En Lin, Feiteng Fang +5
Instruction following (IF) is a critical capability for large language models (LLMs). However, handling complex instructions with multiple constraints remains challenging. Previous…
Adaptive Social Learning via Mode Policy Optimization for Language Agents
Minzheng Wang, Yongbin Li, Haobo Wang +6
Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current studies. Existing methods either lac…
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
Zhuoqun Li, Haiyang Yu, Xuanang Chen +6
Designing solutions for complex engineering challenges is crucial in human production activities. However, previous research in the retrieval-augmented generation (RAG) field has n…
Debate Helps Weak-to-Strong Generalization
Hao Lang, Fei Huang, Yongbin Li
Common methods for aligning already-capable models with desired behavior rely on the ability of humans to provide supervision. However, future superhuman models will surpass the ca…
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
Minzheng Wang, Xinghua Zhang, Kun Chen +5
Large language models (LLMs) enabled dialogue systems have become one of the central modes in human-machine interaction, which bring about vast amounts of conversation logs and inc…
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
Xinghua Zhang, Haiyang Yu, Cheng Fu +2
In the realm of large language models (LLMs), the ability of models to accurately follow instructions is paramount as more agents and applications leverage LLMs for construction, w…
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Zhuoqun Li, Xuanang Chen, Haiyang Yu +7
Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with k…
Transferable Post-training via Inverse Value Learning
Xinyu Lu, Xueru Wen, Yaojie Lu +6
As post-training processes utilize increasingly large datasets and base models continue to grow in size, the computational demands and implementation challenges of existing algorit…
On the Role of Attention Heads in Large Language Model Safety
Zhenhong Zhou, Haiyang Yu, Xinghua Zhang +6
Large language models (LLMs) achieve state-of-the-art performance on multiple language tasks, yet their safety guardrails can be circumvented, leading to harmful generations. In li…
The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends
Xinghua Zhang, Haiyang Yu, Yongbin Li +3
In the era of large language models (LLMs), a vast amount of conversation logs will be accumulated thanks to the rapid development trend of language UI. Conversation Analysis (CA)…
Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement
Le Yu, Bowen Yu, Haiyang Yu +2
Merging Large Language Models (LLMs) aims to amalgamate multiple homologous LLMs into one with all the capabilities. Ideally, any LLMs sharing the same backbone should be mergeable…
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
Zhenhong Zhou, Haiyang Yu, Xinghua Zhang +3
Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs gen…
Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment
Feifan Song, Bowen Yu, Hao Lang +4
Alignment with human preference prevents large language models (LLMs) from generating misleading or toxic content while requiring high-cost human feedback. Assuming resources of hu…
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
Qiaoyu Tang, Jiawei Chen, Zhuoqun Li +10
The rise of large language models (LLMs) has significantly transformed both the construction and application of information retrieval (IR) systems. However, current interactions be…
SoFA: Shielded On-the-fly Alignment via Priority Rule Following
Xinyu Lu, Bowen Yu, Yaojie Lu +5
The alignment problem in Large Language Models (LLMs) involves adapting them to the broad spectrum of human values. This requirement challenges existing alignment methods due to di…
DialCLIP: Empowering CLIP as Multi-Modal Dialog Retriever
Zhichao Yin, Binyuan Hui, Min Yang +2
Recently, substantial advancements in pre-trained vision-language models have greatly enhanced the capabilities of multi-modal dialog systems. These models have demonstrated signif…