8 papers
ART: Attention Replacement Technique to Improve Factuality in LLMs
Ziqin Luo, Yihao Quan, Xiaofeng Zhang +2
Hallucination in large language models (LLMs) continues to be a significant issue, particularly in tasks like question answering, where models often generate plausible yet incorrec…
RELATE: A Reinforcement Learning-Enhanced LLM Framework for Advertising Text Generation
Jinfang Wang, Jiajie Liu, Jianwei Wu +8
In online advertising, advertising text plays a critical role in attracting user engagement and driving advertiser value. Existing industrial systems typically follow a two-stage p…
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…
RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving
Zepeng Ding, Dixuan Wang, Ziqin Luo +3
Multi-step planning has been widely employed to enhance the performance of large language models (LLMs) on downstream natural language processing (NLP) tasks, which decomposes the…
Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy
Guochao Jiang, Ziqin Luo, Chengwei Hu +2
Many previous models of named entity recognition (NER) suffer from the problem of Out-of-Entity (OOE), i.e., the tokens in the entity mentions of the test samples have not appeared…
ToNER: Type-oriented Named Entity Recognition with Generative Language Model
Guochao Jiang, Ziqin Luo, Yuchen Shi +3
In recent years, the fine-tuned generative models have been proven more powerful than the previous tagging-based or span-based models on named entity recognition (NER) task. It has…