Papers by Chenyang Yang

14 papers
Optimizing Deeper Transformers on Small Datasets (2021.acl-long)

Copied to clipboard

Challenge: a common belief that training deep transformers from scratch requires large datasets is wrong . however, with proper initialization and optimization, the benefits of very deep transformer can carry over to challenging tasks with small datasets.
Approach: They train 48 layers of transformers from pre-trained RoBERTa and 24 relation-aware layers from scratch.
Outcome: The proposed scheme achieves state-of-the-art performance on a text-to-sql parsing benchmark . it uses 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers from scratch .
Out-of-Distribution Generalization in Natural Language Processing: Past, Present, and Future (2023.emnlp-main)

Copied to clipboard

Challenge: Existing literature on the generalization of machine learning models to out-of-distribution data is lacking.
Approach: They propose to present the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.
Outcome: The proposed survey provides the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.
AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach: They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome: The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
PLACES: Prompting Language Models for Social Conversation Synthesis (2023.findings-eacl)

Copied to clipboard

Challenge: Currently, collecting high quality conversational data is expensive and infeasible for many applications . a promising direction is to generate synthetic dialogues by prompting large language models .
Approach: They propose to use expert-written conversations as in-context examples to generate synthetic dialogues by prompting large language models.
Outcome: The proposed approach is generalizable to multi-party conversations, compared to human-collected conversations.
What Prompts Don’t Say: Understanding and Managing Underspecification in LLM Prompts (2026.findings-acl)

Copied to clipboard

Challenge: Under-specified prompts are 2x as likely to regress across model or prompt changes, authors show . eliot safina: a lack of explicit prompts can cause frustrations and failures .
Approach: They propose requirements-aware prompt optimization mechanisms that improve performance by 4.8% over baselines.
Outcome: The proposed mechanisms improve prompt performance by 4.8% over baselines.
Exploiting Rich Textual User-Product Context for Improving Personalized Sentiment Analysis (2023.findings-acl)

Copied to clipboard

Challenge: Typical approaches do not exploit the potential of historical reviews or do not make full use of user/product associations.
Approach: They propose to use historical reviews to initialize user and product representations and incorporate textual associations via a user-product cross-context module.
Outcome: The proposed method outperforms existing state-of-the-art models on IMDb, Yelp and Longformer benchmarks.
Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)

Copied to clipboard

Challenge: Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking.
Approach: They propose an iterative adversarial training method that incorporates three key innovations to address these challenges.
Outcome: Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%.
Beyond Testers’ Biases: Guiding Model Testing with Knowledge Bases using LLMs (2023.findings-emnlp)

Copied to clipboard

Challenge: Identifying what to test is a step that is largely ignored and poorly supported.
Approach: They propose an interactive tool that supports requirements elicitation for guiding model testing.
Outcome: The proposed tool can help practitioners test models in real-world settings .
SPHERE: An Evaluation Card for Human-AI Systems (2025.findings-acl)

Copied to clipboard

Challenge: Existing evaluation methods and standards for human-AI systems are unclear, especially for large language models.
Approach: They propose an evaluation card SPHERE which provides a template for evaluation protocols . they outline current evaluation practices and areas for improvement .
Outcome: The evaluation card provides a template for designing evaluation protocols . it outlines current evaluation practices and areas for improvement .
Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)

Copied to clipboard

Challenge: Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations.
Approach: They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation.
Outcome: The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement.
SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science (2025.acl-long)

Copied to clipboard

Challenge: Seed science is essential for modern agriculture, but its application in seed science remains limited due to a shortage of experts and limited availability of online resources.
Approach: They evaluate 26 leading large language models and compare them against a set of benchmarks . they find that there is a gap between the power of LLMs and real-world seed science problems .
Outcome: The new seed benchmark highlights the gap between the power of large language models and real-world seed science problems.
Improving Text Generation with Student-Forcing Optimal Transport (2020.emnlp-main)

Copied to clipboard

Challenge: Maximum likelihood estimation (MLE) is used to train models, but during testing, the model is conditioned on previously generated tokens, resulting in exposure bias.
Approach: They propose to use optimal transport to match the sequences generated in MLE and test modes to reduce exposure bias.
Outcome: The proposed method is validated on machine translation, text summarization, and text generation tasks.
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code.
Approach: They propose a structure-aware method that breaks large AST nodes into smaller chunks . this method generates self-contained, semantically coherent units across programming languages .
Outcome: The proposed method boosts Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation.
ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Activation sparsity is a promising paradigm for accelerating model inference . few large language models achieve high activation spar and comparable performance .
Approach: They propose a method to achieve activation sparsity and acceleration in large language models . they introduce ReLU activation and adopt progressive sparse regularization .
Outcome: The proposed method achieves high activation sparsity and comparable model 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