From the 1 of 70 linked papers with an AI index.
1 citations · 1 across the 18 of their papers we have counts for
9 papers · 1 filter
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
Lihao Sun, Hang Dong, Bo Qiao +3
This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses fu…
G-KV: Decoding-Time KV Cache Eviction with Global Attention
Mengqi Liao, Lu Wang, Chaoyun Zhang +7
Recent reasoning large language models (LLMs) excel in complex tasks but encounter significant computational and memory challenges due to long sequence lengths. KV cache compressio…
WarriorMath: Enhancing the Mathematical Ability of Large Language Models with a Defect-aware Framework
Yue Chen, Minghua He, Fangkai Yang +9
Large Language Models (LLMs) excel in solving mathematical problems, yet their performance is often limited by the availability of high-quality, diverse training data. Existing met…
Self-Evolved Reward Learning for LLMs
Chenghua Huang, Zhizhen Fan, Lu Wang +7
Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversationa…
Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?
Yudi Zhang, Lu Wang, Meng Fang +8
Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the pote…
CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling
Taneesh Gupta, Shivam Shandilya, Xuchao Zhang +5
Reward modeling in large language models is susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily…