Papers by Yuyang Huang

7 papers
Code Representation Pre-training with Complements from Program Executions (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing languages have syntactic representations of code to improve code intelligence, but they are difficult to learn from code.
Approach: They propose to embed dynamic information of programs revealed by their test cases into feature representations of code as complements.
Outcome: The proposed method yields 6%/19% mAP improvements over its masked language modeling counterparts.
BotEval: Facilitating Interactive Human Evaluation (2024.acl-demos)

Copied to clipboard

Challenge: Using language models to perform complex interactive tasks is becoming more common with the rapid progress in natural language processing (NLP) models.
Approach: They develop an evaluation toolkit that enables human-bot interactions as part of the evaluation process.
Outcome: The evaluation toolkit enables human-bot interactions as part of the evaluation process, rather than making judgements for a static input.
DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)

Copied to clipboard

Challenge: Existing preference-based reward modeling methods face a recursive dependency where each verifier requires a meta-verifier, leading to continuous and costly dependence on human annotation.
Approach: They propose a dual RM that couples discriminative and generative reward models under a non-parametric meta-reward.
Outcome: The proposed model achieves strong performance across major preference benchmarks and even when trained exclusively on language modality, it exhibits robust cross-modal transfer on Omni-RewardBench.
Worldwide LiveVQA: Real-Time Visual Knowledge Seeking and Updating Across Languages (2026.findings-acl)

Copied to clipboard

Challenge: Existing resources for visual knowledge remain confined to English, creating a "Worldwide Knowledge Gap" eric liu: production and dissemination of knowledge exhibit a distinct trend toward decentralization and linguistic fragmentation.
Approach: They propose a dataset for multilingual visual knowledge seeking and updating across ten major languages.
Outcome: The proposed dataset is the first dynamic-updating dataset for multilingual visual knowledge seeking and updating across ten major languages.
FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosure (2026.acl-demo)

Copied to clipboard

Challenge: FinReporting is an agentic workflow for localized cross-jurisdiction financial reporting . existing approaches assume a single-market setting and overlook structural differences across jurisdictions .
Approach: They propose a workflow that decomposes financial reporting into auditable stages . they use Large Language Models to extract and summarize corporate disclosures .
Outcome: The proposed system decomposes reporting into auditable stages . it improves consistency and reliability under heterogeneous reporting regimes.
Can Language Model Moderators Improve the Health of Online Discourse? (2024.naacl-long)

Copied to clipboard

Challenge: Existing efforts to automate conversational moderation have focused on banning harmful comments or deleting them, but such efforts can inadvertently push users towards echo chambers that exacerbate polarization.
Approach: They propose a framework to assess models’ moderation capabilities independently of human intervention and propose 'conversational moderation' they propose to use language models as conversational moderators to provide specific feedback on toxic behavior but struggle to influence users to increase their levels of respect and cooperation.
Outcome: The proposed framework assesses models’ moderation capabilities independently of human intervention and shows that appropriately prompted models provide specific and fair feedback on toxic behavior but struggle to influence users to increase their levels of respect and cooperation.
Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals .
Approach: They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation.
Outcome: The proposed method mitigates behavior collapse and improves performance across benchmarks.

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