8 citations · 15 across the 8 of their papers we have counts for
9 papers
Choosing How to Remember: Adaptive Memory Structures for LLM Agents
Mingfei Lu, Mengjia Wu, Feng Liu +8
Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer…
FlashThink: An Early Exit Method For Efficient Reasoning
Guochao Jiang, Guofeng Quan, Zepeng Ding +3
Large Language Models (LLMs) have shown impressive performance in reasoning tasks. However, LLMs tend to generate excessively long reasoning content, leading to significant computa…
AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent Interaction
Zhe Hu, Hou Pong Chan, Yu Yin
Argument generation is a challenging task in natural language processing, which requires rigorous reasoning and proper content organization. Inspired by recent chain-of-thought pro…
MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective
Zhe Hu, Hou Pong Chan, Lifu Huang
Teaching neural models to generate narrative coherent texts is a critical problem. Recent pre-trained language models have achieved promising results, but there is still a gap betw…
PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation
Zhe Hu, Hou Pong Chan, Jiachen Liu +3
Despite recent progress of pre-trained language models on generating fluent text, existing methods still suffer from incoherence problems in long-form text generation tasks that re…
Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
Zhe Hu, Zhiwei Cao, Hou Pong Chan +4
Controllable text generation is an appealing but challenging task, which allows users to specify particular attributes of the generated outputs. In this paper, we propose a control…
Context-Aware Interaction Network for Question Matching
Zhe Hu, Zuohui Fu, Yu Yin +1
Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations. Ho…
An Entity-Driven Framework for Abstractive Summarization
Eva Sharma, Luyang Huang, Zhe Hu +1
Abstractive summarization systems aim to produce more coherent and concise summaries than their extractive counterparts. Popular neural models have achieved impressive results for…
Argument Generation with Retrieval, Planning, and Realization
Xinyu Hua, Zhe Hu, Lu Wang
Automatic argument generation is an appealing but challenging task. In this paper, we study the specific problem of counter-argument generation, and present a novel framework, CAND…