Zepeng Ding
YOU?
Author Swipe
View article: FlashThink: An Early Exit Method For Efficient Reasoning
FlashThink: An Early Exit Method For Efficient Reasoning Open
Large Language Models (LLMs) have shown impressive performance in reasoning tasks. However, LLMs tend to generate excessively long reasoning content, leading to significant computational overhead. Our observations indicate that even on sim…
View article: RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving
RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving Open
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 original task into multiple subtasks and guide LLMs to solv…
View article: Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy
Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy Open
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 in the training samples, which hinders the achievement of …
View article: Adaptive Reinforcement Learning Planning: Harnessing Large Language Models for Complex Information Extraction
Adaptive Reinforcement Learning Planning: Harnessing Large Language Models for Complex Information Extraction Open
Existing research on large language models (LLMs) shows that they can solve information extraction tasks through multi-step planning. However, their extraction behavior on complex sentences and tasks is unstable, emerging issues such as fa…
View article: Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization
Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization Open
Large Language Models (LLMs) have shown remarkable capabilities in language understanding and generation. Nonetheless, it was also witnessed that LLMs tend to produce inaccurate responses to specific queries. This deficiency can be traced …
View article: P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models
P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models Open
In recent years, the rise of large language models (LLMs) has made it possible to directly achieve named entity recognition (NER) without any demonstration samples or only using a few samples through in-context learning (ICL). However, sta…
View article: Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction
Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction Open
Relation triple extraction, which outputs a set of triples from long sentences, plays a vital role in knowledge acquisition. Large language models can accurately extract triples from simple sentences through few-shot learning or fine-tunin…