4 citations · 5 across the 16 of their papers we have counts for
11 papers · 1 filter
Tensorizing Engram: Sharing Latents Across N-Gram Embeddings is Beneficial in LLMs
Wuyang Zhou, Yuxuan Gu, Giorgos Iacovides +3
Modern language models represent text using discrete token-level embeddings, which forces recurring multi-token patterns to be learned implicitly across Transformer layers. Both Ov…
Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation?
Yuxuan Gu, Lunjun Liu, Xiaocheng Feng +4
An essential problem in artificial intelligence is whether LLMs can simulate human cognition or merely imitate surface-level behaviors, while existing datasets suffer from either s…
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Lei Huang, Xiang Cheng, Chenxiao Zhao +6
Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorit…
Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering
Kun Zhu, Lizi Liao, Yuxuan Gu +3
The rapid growth of scientific literature demands efficient methods to organize and synthesize research findings. Existing taxonomy construction methods, leveraging unsupervised cl…
Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization
Lei Huang, Xiaocheng Feng, Weitao Ma +9
Ensuring contextual faithfulness in retrieval-augmented large language models (LLMs) is crucial for building trustworthy information-seeking systems, particularly in long-form ques…
Length Controlled Generation for Black-box LLMs
Yuxuan Gu, Wenjie Wang, Xiaocheng Feng +5
Large language models (LLMs) have demonstrated impressive instruction following capabilities, while still struggling to accurately manage the length of the generated text, which is…