13 papers
Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off
Zhiyuan Cheng, Longying Lai, Yue Liu
Retrieval-Augmented Generation (RAG) systems for financial document QA typically follow a chunk-based paradigm: documents are split into fragments, embedded, and retrieved by simil…
Attribute-Grounded Selective Reasoning for Artwork Emotion Understanding with Multimodal Large Language Models
Cheng Zhang, Yuer Liu, Zhiyu Zhou +2
Multimodal large language models (MLLMs) can produce fluent artwork emotion explanations, but they often suffer from attribute flooding: they enumerate many visible formal attribut…
OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention
Chenyu Zhou, Hongpei Li, Yuerou Liu +3
Linear attention and state-space models offer constant-memory alternatives to softmax attention, but often struggle with in-context associative recall. The Delta Rule mitigates thi…
Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis
Zhiyuan Cheng, Longying Lai, Yue Liu +2
Financial analysts face significant challenges extracting information from lengthy 10-K reports, which often exceed 100 pages. This paper presents a Retrieval-Augmented Generation…
Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning
Jingxiang Chen, Minseok Kim, Seong-Gyun Leem +13
Speech large language models (LLMs) observe paralinguistic cues such as prosody, emotion, and non-verbal sounds--crucial for intent understanding. However, leveraging these cues fa…
Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-Tuning
Derin Cayir, Renjie Tao, Rashi Rungta +6
Large Language Models (LLMs) have demonstrated remarkable progress through preference-based fine-tuning, which critically depends on the quality of the underlying training data. Wh…