Papers by Bryan Zhang

12 papers
Leveraging Product Catalog Patterns for Multilingual E-commerce Product Attribute Prediction (2025.emnlp-industry)

Copied to clipboard

Challenge: E-commerce stores increasingly use Large Language Models to improve catalog data quality . a critical challenge is accurately predicting missing structured attribute values .
Approach: They propose a retrieval-augmented system that leverages existing product catalog entries to guide LLM predictions for missing attributes.
Outcome: The proposed system improves catalog data quality by 34% and accuracy by 0.8% . the proposed model can predict missing attributes in multilingual product catalogs .
Scaling Laws for Code: Every Programming Language Matters (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on language-agnostic settings, neglecting the inherently multilingual nature of modern software development.
Approach: They propose a proportion-dependent scaling law that prioritizes high-utility languages . they propose PLs to have varying effects during pre-training that affect model performance .
Outcome: The proposed scaling law is based on 1000+ experiments across multiple languages and models.
LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach: They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome: The proposed model achieves comparable performance to standard dense models with more parameters.
SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres (2023.acl-long)

Copied to clipboard

Challenge: Experiments on two unified-annotated event datasets indicate that SPEECH is predominant in event detection and event-relation extraction tasks.
Approach: They propose to model complex dependency among event structured components with energy-based energy-modeling and represent event classes with simple but effective hyperspheres.
Outcome: Experiments on two unified-annotated event datasets show that SPEECH is predominant in event detection and event-relation extraction tasks.
ReLearn: Unlearning via Learning for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for unlearning large language models often rely on reverse optimization to reduce target token probabilities.
Approach: They propose a data augmentation and fine-tuning pipeline for effective unlearning . they propose augmentation, evaluation frameworks to measure contextual forgetting .
Outcome: The proposed framework achieves targeted forgetting while preserving high-quality outputs.
Machine-Generated Text Localization (2024.findings-acl)

Copied to clipboard

Challenge: Prior work focused on identifying only part of a document as machine or human written . a key challenge is that short spans of text provide little information indicating if it is machine generated due to its short length .
Approach: They propose a method that localizes the portions of a document that were machine generated.
Outcome: The proposed method can detect changes in style or content to boost performance.
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines (2025.naacl-long)

Copied to clipboard

Challenge: Vision Language Models struggle with cultural-specific knowledge, especially in languages other than English and in underrepresented cultural contexts.
Approach: They propose a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects and a training dataset.
Outcome: The proposed model performs better with correct location context, but struggles with adversarial contexts and predicting specific regional cuisines and languages.
Safety in Large Reasoning Models: A Survey (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Reasoning Models (LRMs) have a high level of advanced reasoning capabilities, but they are vulnerable and vulnerable.
Approach: This paper presents the first comprehensive survey of Large Reasoning Models . it explores the new safety risks, attacks, and defense strategies specific to LRMs based on reasoning .
Outcome: The proposed study examines the safety and security risks of large reasoning models.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

Copied to clipboard

Challenge: Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach: They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome: The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.
Machine translation impact in E-commerce multilingual search (2022.emnlp-industry)

Copied to clipboard

Challenge: Existing studies have demonstrated that cross-lingual information retrieval performance is highly dependent on query translation quality.
Approach: They investigate whether improving query translation quality yields little or no benefit to further improve retrieval performance.
Outcome: The proposed methods compare query translations for multiple language pairs and identify the most promising language pairs to invest and improve.
Discovering Language Model Behaviors with Model-Written Evaluations (2023.findings-acl)

Copied to clipboard

Challenge: Prior work creates evaluations with crowdwork or existing data sources, which are not always available.
Approach: They generate evaluations automatically with language models (LMs) using crowdwork or existing data sources to find out how they behave .
Outcome: The results show that large LMs repeat back a dialog user’s preferred answer and express greater desire to pursue concerning goals like resource acquisition and goal preservation.
Show, Write, and Retrieve: Entity-aware Article Generation and Retrieval (2023.findings-emnlp)

Copied to clipboard

Challenge: Prior work typically encodes all tokens in articles using pre-trained language models, however, many named entities are difficult to accurately recognize and predict by language models.
Approach: They propose an ENtity-aware article GeneratIoN and rEtrieval framework to explicitly incorporate named entities into language models.
Outcome: The proposed framework can boost article generation and retrieval performance, with a 4-5 perplexity improvement in article generation, and a 3-4% boost in recall@1 in article retrieval.

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