Papers by Xiang Qian

10 papers
ReCode: Robustness Evaluation of Code Generation Models (2023.acl-long)

Copied to clipboard

Challenge: Existing work on robustness in text or code tasks has focused on classification, while robustness for code generation tasks is an uncharted area.
Approach: They propose a robustness evaluation benchmark for code generation models that customizes over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format.
Outcome: The proposed model performs better on human annotators and on SOTA models with human annnotators.
UniLG: A Unified Structure-aware Framework for Lyrics Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing works ignore musical attributes hidden behind lyrics and structure of lyrics . existing works ignore structure of generated lyrics and do not consider structure of songs .
Approach: They propose a framework for conditional lyrics generation that considers structure and relationship between lyrics and music.
Outcome: The proposed framework improves the structure modeling and unifies different conditions for different types of lyrics generation.
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for MLM agents in interactive environments are limited by their focus on a single environment, lack of detailed and generalized evaluation methods, and the complexity of constructing tasks and evaluators.
Approach: They propose a cross-environment agent benchmark framework that integrates graph-based evaluation and task generation methods.
Outcome: The proposed framework supports multiple devices and can be easily extended to any environment with a Python interface.
Training-Free Adaptive Speculative Decoding via Linguistic Priors (2026.findings-acl)

Copied to clipboard

Challenge: Speculative decoding (SPD) is a promising technique to accelerate Large Language Models (LLMs). current approaches neglect the inherent heterogeneity of natural language and fail to distinguish between semantically-rich content and structurally-predictable syntax.
Approach: They propose a training-free framework that leverages linguistic priors to enable adaptive drafting and verification.
Outcome: The proposed framework significantly accelerates inference without additional training.
Improved Policy Optimization for Mixture-of-Experts Models: Importance Sampling and Rewarding from an Expert-Centric Perspective (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to reinforcement learning (RL) suffer from training instability . existing approaches often ignore token-specific discrepancies in expert assignments .
Approach: They propose to introduce expert-level importance sampling to reduce complexity of RL . they propose to leverage expert-centric granularity to ensure a rigorous alignment between reward signals and policy updates.
Outcome: The proposed method outperforms strong baselines across reasoning tasks.
Initializing and Retrofitting Key-Value Adaptors for Traceable Model Editing (2025.findings-acl)

Copied to clipboard

Challenge: Language models (LMs) are becoming imperative tools for consulting in realworld scenarios.
Approach: They propose a model editing method that initializes and retrofits key-value pairs into MLP blocks to construct a new mapping of a piece of knowledge without damaging irrelevant knowledge.
Outcome: The proposed method outperforms baseline methods on a series of GPT series models on edit success and generalization without influencing specificity.
Probing the Plasticity and Correlation of LLM Value Systems: LLM Value Rankings are Not Stable (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have similar value rankings but little is known about how susceptible they are to external influence and how different values are correlated with each other.
Approach: They propose to use 6 different value transformation prompting methods to examine the plasticity of LLM value systems by comparing them with 8 LLMs.
Outcome: The proposed methods are effective on 8 LLMs and 3 families.
TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction (2023.findings-emnlp)

Copied to clipboard

Challenge: ChatGPT and GPT-4 are commercial large language models (LLMs) however, they may produce vague responses or incorrect answers in certain specialized domains.
Approach: They propose a token compression scheme that uses summarization and semantic compression to reduce the token size of LLMs.
Outcome: The proposed method reduces token size by doing summarization and semantic compression while reducing token size with only 1.6% accuracy drop.
Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance (2025.emnlp-main)

Copied to clipboard

Challenge: Greek is the dominant language of the world's merchant navy and is a key language for international trade.
Approach: They propose to develop a Greek financial evaluation benchmark and a financial LLM fine-tuned on Greek-specific financial data to bridge this gap.
Outcome: The proposed benchmarks surpass GPT-4 by 8.33%, GPT- 4o by 26.83%, and Deepseek-V3 by 67.74%.

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