Papers by Zhensheng Wang

5 papers
Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions (2026.findings-acl)

Copied to clipboard

Challenge: Existing automation methods follow fixed template filling and cannot support dynamic updates for diverse, user-authored decks.
Approach: They propose a framework that combines multimodal slide parsing, natural language instruction grounding, and tool-augmented reasoning for tables, charts, and textual conclusions.
Outcome: The proposed framework updates content while preserving layout and style while maintaining a strong reference baseline on DynaSlide.
ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to train LLMs suffer from overthinking, leading to lengthy reasoning traces . Existing approaches to train large language models suffer from this problem .
Approach: They propose a method to combine multiple reasoning chains for training LLMs . they use stepwise exploration and long-short switched sampling to evaluate reasoning paths .
Outcome: The proposed method reduces reasoning lengths by approximately 30-50% . it also maintains or improves reasoning accuracy compared to baselines .
EVGeoQA: Benchmarking LLMs on Dynamic, Multi-Objective Geo-Spatial Exploration (2026.findings-acl)

Copied to clipboard

Challenge: Existing geo-spatial question answering benchmarks focus on static retrieval, failing to capture the complexity of real-world planning that involves dynamic user locations and compound constraints.
Approach: They propose a new benchmark for Large Language Models that integrates location-anchored and dual-objective queries with a user's real-time coordinates.
Outcome: The proposed model can summarize historical exploration trajectories to enhance exploration efficiency.
ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing tabular question answering systems cannot perform future-oriented numerical prediction . open-domain tabular questions are a popular approach for QA tasks .
Approach: They propose a task that covers time-series forecasting and forecast-based reasoning scenarios using real estate data.
Outcome: The proposed framework decomposes the problem into three collaborative roles that synthesize the results to construct a precise and consistent final answer.
ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to tabular QA are limited to closed-domain scenarios . existing approaches do not solve the core challenge of generating correct answers without user clarification .
Approach: They propose a benchmark to tackle underspecified or uncertain queries in tabular question answering . they propose ODUTQA-MDC task and a multi-agent framework to detect ambiguities .
Outcome: The proposed framework excels at detecting ambiguities, clarifying them through dialogue, and refining answers.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations