ALARM: Align Language Models via Hierarchical Rewards Modeling
ALARM introduces a framework for aligning large language models with human preferences through hierarchical rewards modeling in reinforcement learning.
LLM: Induction through Deduction Framework
LLMs can enhance induction through deduction.
PipeRAG: Enhancing Efficiency in Retrieval-Augmented Generation
PipeRAG improves generation efficiency through pipeline parallelism, flexible retrieval intervals, and performance modeling.
(Chat)GPT vs BERT: Semantic Change Detection Study
(Chat)GPT performs worse than BERT in detecting short-term semantic changes but slightly lower in long-term changes.
Few-shot Relation Extraction with CoT-ER Approach
Large language models can effectively perform few-shot relation extraction tasks with the CoT-ER approach, outperforming fully-supervised methods.
ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications
ACLSum introduces a novel dataset for multi-aspect summarization of scientific papers, addressing the limitations of existing resources.
Se2: Sequential Example Selection for In-Context Learning
Se2은 순차적 선택 방법을 통해 In-Context Learning을 향상시키는 효과적인 방법을 제안합니다.
OATS: Aspect-Based Sentiment Analysis Dataset and Experiments
OATS dataset introduces new domains and comprehensive annotations for ABSA tasks, aiming to bridge gaps in existing datasets and enhance ABSA research.
KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions
LLMs struggle to follow diverse instructions in knowledge-intensive writing tasks, highlighting the need for improvement.
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
LoRAMoE introduces a novel framework to address the conflict between improving LLM performance on downstream tasks and preventing world knowledge forgetting during SFT.
