6 papers
BoRP: Bootstrapped Regression Probing for Scalable and Human-Aligned LLM Evaluation
Peng Sun, Xiangyu Zhang, Duan Wu +5
Accurate evaluation of user satisfaction is critical for iterative development of conversational AI. However, for open-ended assistants, traditional A/B testing lacks reliable metr…
Boosting Direct Preference Optimization with Penalization
Pengwei Sun
Offline preference optimization has become a practical substitute for reinforcement learning from human feedback, but pairwise objectives such as Direct Preference Optimization (DP…
AIonopedia: an LLM agent orchestrating multimodal learning for ionic liquid discovery
Yuqi Yin, Yibo Fu, Siyuan Wang +8
The discovery of novel Ionic Liquids (ILs) is hindered by critical challenges in property prediction, including limited data, poor model accuracy, and fragmented workflows. Leverag…
Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
Senjie Jin, Lu Chen, Zhiheng Xi +9
Natural language chain-of-thought (N-CoT) and Program chain-of-thought (P-CoT) have emerged as two primary paradigms for large language models (LLMs) to solve mathematical reasonin…
Causal Attention with Lookahead Keys
Zhuoqing Song, Peng Sun, Huizhuo Yuan +1
In standard causal attention, each token's query, key, and value (QKV) are static and encode only preceding context. We introduce CAuSal aTtention with Lookahead kEys (CASTLE), an…
ReFT: Reasoning with Reinforced Fine-Tuning
Trung Quoc Luong, Xinbo Zhang, Zhanming Jie +3
One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does…