activity
20242026
collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

Fast Numbers, Slow Language: Bridging Quantitative and Qualitative Earnings Signals

Ding Yu, Zhuo Liu, Hao Zhang +1

Earnings announcements release two types of information sequentially: quantitative surprise (numeric earnings-per-share (EPS)/revenue versus analyst estimate) arrives first in pres…

cs.CL2026

Style or Content? Evaluating Style Classifiers with Controlled Content Overlap

Zhuo Liu, Haozheng Du, Xiangxiang Xu +1

Style classifiers can use content cues that correlate with style labels in naturally collected data, yet we lack a systematic way to measure this reliance. We study this problem wi…

cs.CL2025

TreeRare: Syntax Tree-Guided Retrieval and Reasoning for Knowledge-Intensive Question Answering

Boyi Zhang, Zhuo Liu, Hangfeng He

In real practice, questions are typically complex and knowledge-intensive, requiring Large Language Models (LLMs) to recognize the multifaceted nature of the question and reason ac…

cs.CL2025

Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting

Jiarui Wu, Zhuo Liu, Hangfeng He

Spatial relation hallucinations pose a persistent challenge in large vision-language models (LVLMs), leading to generate incorrect predictions about object positions and spatial co…

cs.CL2024

Same Company, Same Signal: The Role of Identity in Earnings Call Transcripts

Ding Yu, Zhuo Liu, Hangfeng He

Post-earnings volatility prediction is critical for investors, with previous works often leveraging earnings call transcripts under the assumption that their rich semantics contrib…