Papers by Yongheng Wang

5 papers
ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for fine-tuning-based compression suffer from verbose outputs, increasing computational overhead.
Approach: They propose a framework to generate concise reasoning chains using Confidence Injection and Early Stopping.
Outcome: The proposed framework reduces the length of the model by up to 50% while maintaining high task accuracy.
Can We Edit Multimodal Large Language Models? (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods to edit multimodal models have been used to incrementally infuse a language model with a new set of facts.
Approach: They construct a benchmark for editing multimodal Large Language Models and establish metrics for evaluation.
Outcome: The proposed benchmarks show that editing multimodal models is not as difficult as editing single-modal models.
Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information (2024.findings-emnlp)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) is a key technique for enhancing the performance of Large Language Models.
Approach: They propose a framework that optimizes outputs by utilizing wrong information and multi-perspective verification.
Outcome: The proposed framework surpasses all baselines on 8 datasets and 5 LLMs.
CoTrust: Privacy-Preserving Collaboration Between Large and Small Language Models in Trusted Execution Environments (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) provide powerful text generation capabilities, but accessing sensitive user inputs raises privacy concerns.
Approach: They propose a privacy-preserving collaborative inference framework that combines large language models with small language models inside TEE to preserve privacy.
Outcome: Experiments show that CoTrust outperforms unconstrained LLMs on multiple question answering and summarization benchmarks while maintaining strong privacy protection.
HTCCN: Temporal Causal Convolutional Networks with Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs (2024.naacl-long)

Copied to clipboard

Challenge: Temporal knowledge graphs (TKGs) are powerful tools for storing and modeling dynamic facts.
Approach: They propose a Hawkes process-based temporal causal convolutional network for temporal reasoning under extrapolation settings.
Outcome: The proposed network is based on Hawkes process-based temporal causal convolutional network and captures the temporal evolution of facts.

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