7 papers
Synthetic Perception: Can Generated Images Unlock Latent Visual Prior for Text-Centric Reasoning?
Yuesheng Huang, Peng Zhang, Xiaoxin Wu +2
A significant ``modality gap" exists between the abundance of text-only data and the increasing power of multimodal models. This work systematically investigates whether images gen…
The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulation
Huiqi Deng, Qihan Ren, Zhuofan Chen +5
Understanding what kinds of cooperative structures deep neural networks (DNNs) can represent remains a fundamental yet insufficiently understood problem. In this work, we treat int…
Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling
Pengfei Wang, Baolin Sun, Xuemei Dong +7
State-of-the-art (SOTA) Text-to-SQL methods still lag significantly behind human experts on challenging benchmarks like BIRD. Current approaches that explore test-time scaling lack…
Differentiated Directional Intervention A Framework for Evading LLM Safety Alignment
Peng Zhang, Peijie Sun
Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direc…
InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior
Huisheng Wang, Zhuoshi Pan, Hangjing Zhang +3
Aligning Large Language Models (LLMs) with investor decision-making processes under herd behavior is a critical challenge in behavioral finance, which grapples with a fundamental l…
Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation
Xiangju Li, Dong Yang, Xiaogang Zhu +3
Span-level emotion-cause-category triplet extraction represents a novel and complex challenge within emotion cause analysis. This task involves identifying emotion spans, cause spa…