Papers by Hong Xie

10 papers
Reconstruction Attack on Instance Encoding for Language Understanding (2021.emnlp-main)

Copied to clipboard

Challenge: Existing private learning schemes which protect data privacy can be used to train models using instance encoding.
Approach: They propose to recover the private training data and use it to break a private learning scheme TextHide.
Outcome: The proposed attack would advance privacy-preserving machine learning in the context of natural language processing.
Reflect, Rewrite, Repeat: How Simple Arithmetic Enables Advanced Reasoning in Small Language Models (2026.findings-eacl)

Copied to clipboard

Challenge: Recent advances in language model reasoning require computationally intensive reinforcement learning and massive datasets.
Approach: They propose a framework that combines Direct Preference Optimization and Supervised Fine-Tuning with selective guidance from larger models and iteratively refining solutions through a "reflect, rewrite, repeat" cycle.
Outcome: The proposed framework shows significant performance improvements across arithmetic, symbolic and cognitive reasoning benchmarks.
SubDocTrans: Enhancing Document-level Machine Translation with Plug-and-play Multi-granularity Knowledge Augmentation (2025.findings-emnlp)

Copied to clipboard

Challenge: Document translations generated by large language models suffer from poor consistency, weak coherence, and omission errors.
Approach: They propose a document-level machine translation framework that extracts knowledge from documents to produce high-quality translations.
Outcome: The proposed framework improves consistency and coherence, reduces omission errors, and mitigates hallucinations.
Understanding and Patching Compositional Reasoning in LLMs (2024.findings-acl)

Copied to clipboard

Challenge: LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
Approach: They propose a lightweight method to patch compositional reasoning errors via editing the located MHSA modules in LLMs.
Outcome: The proposed method can be used to patch compositional reasoning errors using MHSA modules located within the layers of the LLMs.
Adaptive Textual Label Noise Learning based on Pre-trained Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to learning with noisy labels are limited due to the time and labor costs involved.
Approach: They propose an adaptive warm-up and hybrid training frameworks to learn with noisy labels based on pre-trained models.
Outcome: The proposed approach performs comparable or even surpasses state-of-the-art methods in various noise scenarios, including scenarios with the mixture of multiple types of noise.
Can AI Revise Research Papers with Human Review Feedback? An Empirical Study and Benchmark (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are fundamentally reshaping the scientific landscape, transitioning the role of AI from passive tools to active partners within a new paradigm of Human-AI collaboration.
Approach: They propose a benchmark to evaluate the ability of Large Language Models to improve papers with human feedback.
Outcome: The proposed benchmark tests the skills of Large Language Models (LLMs) on paper interpretation, experimental implementation, and paper formulation, using authors’ camera-ready versions as natural human baselines.
The Model Agreed, But Didn’t Learn: Diagnosing Surface Compliance in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models internalize vast world knowledge as parametric memory, yet inherit the staleness and errors of their source corpora.
Approach: They propose a framework that subjects models to discriminative self-assessment under diverse contextual pressures to scrutinize subtle behavioral nuances induced by memory modifications.
Outcome: The proposed framework achieves high benchmarks without overwriting internal beliefs, while recursive modifications accumulate representational residues, triggering cognitive instability and permanently diminishing the reversibility of the model’s memory state.
Exploring the Choice Behavior of Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly being adopted across various domains where they help to make choices.
Approach: They construct a virtual QA platform that includes three different experimental conditions, with four models from GPT and Llama series participating in repeated experiments.
Outcome: The proposed model includes three experimental conditions and four models from GPT and Llama series.
Differentially Private Instance Encoding against Privacy Attacks (2022.naacl-srw)

Copied to clipboard

Challenge: TextHide is a proposed privacy-enhancing technology to protect the training data from privacy attacks.
Approach: They propose to encode training data via instance encoding in natural language domain without theoretic privacy guarantee.
Outcome: The proposed scheme can defend against privacy attacks while ensuring learning utility (as a trade-off).
CoAlign: Uncertainty Calibration of LLM for Geospatial Repartition (2025.acl-industry)

Copied to clipboard

Challenge: Existing methods to optimize geospatial repartition rely on manual adjustments by experts or algorithmic optimization using limited offline operational metrics.
Approach: They propose a framework that calibrates LLM uncertainty to enable robust geospatial repartition by integrating historical data with LLM-generated candidates.
Outcome: The proposed framework calibrates LLM uncertainty to enable robust geospatial repartition by integrating historical data with LLM-generated candidates.

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