Papers by Huiming Wang

7 papers
Re3Syn: A Dependency-Based Data Synthesis Framework for Long-Context Post-training (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for constructing long-context data by concatenating short documents have overlooked a crucial characteristic of long-constituency data quality, semantic dependency.
Approach: They propose a framework called Retrieval, Dependency Recognition, and Reorder for data synthesis which leverages semantic similarity to retrieve relevant documents and form several batches.
Outcome: The proposed framework leverages semantic similarity to retrieve relevant documents and form several batches.
CLaSp: In-Context Layer Skip for Self-Speculative Decoding (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for drafting Large Language Models require additional modules to be trained, which can be challenging to implement and ensure compatibility across various LLMs.
Approach: They propose an in-context layer-skipping strategy for self-speculative decoding that uses a plug-and-play mechanism to skip intermediate layers of the verify model to construct a compressed draft model.
Outcome: The proposed method achieves a speedup of 1.3 1.7 on LLaMA3 series models without altering the original distribution of the generated text.
AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging (2025.naacl-long)

Copied to clipboard

Challenge: Large Language Models excel in highresource languages but underperform in lowresource ones.
Approach: They propose a cross-lingual transfer method that decouples "task ability" from "language ability" they propose to use adaptive adapter merging to obtain target adapters by combining other adapters.
Outcome: The proposed method outperforms existing methods in highresource languages . it decouples "task ability" from "language ability" but fails to fully separate "task capability" from the "source language"
Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition (2024.acl-long)

Copied to clipboard

Challenge: Existing DA methods for named entity recognition (NER) are costly and labor-intensive to acquire, necessitating innovative approaches to data scarcity.
Approach: They propose an order-agnostic data augmentation solution that exploits the order-based property in the training phase of sequence-to-sequence NER methods for data augmented.
Outcome: The proposed method significantly enhances the few-shot capabilities of pre-trained language models in low-resource settings.
How do Language Models Reshape Entity Alignment? A Survey of LM-Driven EA Methods: Advances, Benchmarks, and Future (2025.emnlp-main)

Copied to clipboard

Challenge: Entity alignment (EA) is critical for knowledge graph (KG) integration.
Approach: They propose a taxonomy that categorizes methods in three stages: data preparation, feature embedding, and alignment.
Outcome: The proposed taxonomy categorizes methods in three key stages: data preparation, feature embedding, and alignment.
Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable reasoning capabilities, but they still face challenges in knowledge-intensive multi-hop reasoning.
Approach: They propose a method that uses self-critique feedback to guide iterative reasoning by enabling iteration and self-evaluation of its intermediate reasoning steps.
Outcome: The proposed method surpasses the previous SOTA by 8.6% on three multi-hop reasoning datasets.
Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for training contrastive learning based sentence embedding models are largely influenced by the quality of sentence pairs.
Approach: They propose a framework that decomposes LLMs into three stages for training . they propose to refine the generated content at these stages to ensure only high-quality sentence pairs are utilized to train a base contrastive learning model.
Outcome: The proposed framework surpasses ChatGPT and ChatGPP in terms of performance.

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