4 papers
Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts
Anwesan Pal, Karen Hovsepian, Tinghao Guo +5
Recent investigations into effective context lengths of modern flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reason…
Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models
Kangyang Luo, Zichen Ding, Zhenmin Weng +5
While Chain of Thought (CoT) prompting approaches have significantly consolidated the reasoning capabilities of large language models (LLMs), they still face limitations that requi…
VITA: Towards Open-Source Interactive Omni Multimodal LLM
Chaoyou Fu, Haojia Lin, Zuwei Long +16
The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas.…
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
Junru Lu, Jiazheng Li, Siyu An +4
Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a mor…