12 papers · 1 filter
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
Dingwei Chen, Ziqiang Liu, Feiteng Fang +6
Large Language Models (LLMs) demonstrate remarkable capabilities in text understanding and generation. However, their tendency to produce factually inconsistent outputs, commonly r…
Expression Syntax Information Bottleneck for Math Word Problems
Jing Xiong, Chengming Li, Min Yang +2
Math Word Problems (MWP) aims to automatically solve mathematical questions given in texts. Previous studies tend to design complex models to capture additional information in the…
A Survey on Large Language Model Benchmarks
Shiwen Ni, Guhong Chen, Shuaimin Li +11
In recent years, with the rapid development of the depth and breadth of large language models' capabilities, various corresponding evaluation benchmarks have been emerging in incre…
AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents
Guhong Chen, Liyang Fan, Zihan Gong +8
Current research in LLM-based simulation systems lacks comprehensive solutions for modeling real-world court proceedings, while existing legal language models struggle with dynamic…
Lower Layers Matter: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused
Dingwei Chen, Feiteng Fang, Shiwen Ni +6
Large Language Models (LLMs) have demonstrated exceptional performance across various natural language processing tasks. However, they occasionally generate inaccurate and counterf…
Training on the Benchmark Is Not All You Need
Shiwen Ni, Xiangtao Kong, Chengming Li +4
The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and th…