Papers by Shihao Wang

10 papers
K-order Ranking Preference Optimization for Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing list-wise methods focus on optimizing list ranking consistency for LLMs to improve ranking abilities.
Approach: They propose to extend the Plackett-Luce model to accommodate top-K ranking by extending the DPO’s Plact-Lucer model to dynamically determine appropriate K for different samples.
Outcome: The proposed model can be extended to accommodate top-K ranking and improve training efficiency.
Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing systems for conversational AI are user-driven, but in many real-world situations, they do not extract information to achieve its own objectives.
Approach: They propose an inquisitive conversational agent that learns when and how to ask probing questions . they also propose a framework for a conversational ICA specifically tailored to the court .
Outcome: The proposed method outperforms single-agent RL baselines on a U.S. Supreme Court dataset.
Towards General Agentic Intelligence via Environment Scaling (2026.findings-acl)

Copied to clipboard

Challenge: Diverse real-world APIs require precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments.
Approach: They propose a framework that scales up environments to enable agentic intelligence . they use a two-phase agent fine-tuning strategy to first endow agents with basic agentic capabilities, then specializing them for domain-specific contexts.
Outcome: Experiments on -bench, -Bench, and ACEBench show that the model significantly enhances the models’ function-calling capability.
RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit remarkable capabilities across many tasks, but face critical challenges in the CSC scenario: (1) poor generalization to rare entities in open-domain searches; and (2) failure to adapt to temporal entity variations due to static parameters, resulting in serious over-correction issues.
Approach: They propose a Chinese Spelling Check system with RAG and multi-task learning that integrates dynamic knowledge retrieval and entity-centric RAG to address rare entities.
Outcome: The proposed system outperforms existing baselines in the CSC task and achieves a maximum improvement of +9.92% on the search scenario benchmark and +3.2% on the general-domain dataset.
MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios.
Approach: They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity.
Outcome: The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues.
Pre3: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for structured generation of outputs are inefficient under large inference batches.
Approach: They propose a new LLM-based method that parses LR(1) grammars into a pushdown automaton and exploits deterministic pushdown automation to optimize the constrained LLM decoding efficiency.
Outcome: The proposed method improves time per output token (TPOT) by 40% and throughput by 36% .
Temporal Evidence Chain for Temporal Knowledge Graph Question Answering with Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Temporal Knowledge Graph Question Answering (TKGQA) aims to answer temporal questions using knowledge from Temporal knowledge graphs.
Approach: They propose a framework to construct temporal evidence chains for LLM reasoning using Temporal Knowledge Graphs.
Outcome: TECQA outperforms existing methods on MultiTQ and CronQuestions.
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning.
Approach: They propose a virtual API server and stable evaluation system to assess the stability of large-scale real-time APIs.
Outcome: The proposed benchmarks demonstrate the stability of the proposed system and its caching system.
WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Copied to clipboard

Challenge: Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach: They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome: The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .
U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing context-folding methods are designed for single-query or single-intent scenarios.
Approach: They propose a dynamic context-folding framework tailored to user-centric tasks that preserves fine-grained information through dynamic context folding.
Outcome: The proposed framework outperforms ReAct and previous folding frameworks on long, noisy tasks.

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