Papers by Chenyang Zhao

9 papers
Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods for probability-based UE are limited by their inability to handle biased probabilities and complex semantic dependencies between tokens.
Approach: They propose a learning-based scoring function that captures complex dependencies between tokens and probabilities and produces more reliable responses.
Outcome: The proposed function outperforms existing scoring functions in question-answering and arithmetical reasoning tasks with different datasets.
Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language (2025.acl-long)

Copied to clipboard

Challenge: Existing datasets for instruction-following are monolingual and centered on English . existing data are unable to capture linguistic and cultural subtle differences .
Approach: They propose an extension of IFEval to a localized multilingual version called Marco-Bench-MIF . their benchmark addresses linguistic constraints and cultural references via translation and verification .
Outcome: The proposed extension of IFEval to a localized multilingual version covers 30 languages with varying levels of localization.
VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making (2025.emnlp-main)

Copied to clipboard

Challenge: Recent large-scale pretrained models are built upon a multi-input single-output paradigm . tasks compete for a shared output channel, creating mutual exclusion effects .
Approach: They propose a multi-input single-output (MISO) paradigm for large pretrained models . they propose unified training framework that enables concurrent multi-task outputs .
Outcome: Experiments on autonomous driving platform show that MIMO-VLA outperforms state-of-the-art models in MIMO settings.
Prompt2Model: Generating Deployable Models from Natural Language Instructions (2023.emnlp-demo)

Copied to clipboard

Challenge: Large language models (LLMs) are a step backward from traditional special-purpose NLP models . they require extensive computational resources for deployment and can be gated behind APIs .
Approach: They propose a general-purpose method that takes a natural language task description and uses it to train a special-purpose model.
Outcome: The proposed method outperforms a strong LLM by 20% while being 700 times smaller.
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 .
On the Representation Geometry of LoRA Model Merging (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for low-rank Adaptation (LoRA) fine-tuning focus on globally shared structure . combining SVD with CUR improves performance of LoRA model merging .
Approach: They propose a training-free method that combines SVD and CUR decomposition to improve LoRA merging performance.
Outcome: The proposed procedure improves on vision and language benchmarks.
Unsupervised Melody-to-Lyrics Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for automatic melody-to-lyric generation are limited due to the limited amount of melody-lyrical aligned data.
Approach: They propose a method for automatic melody-to-lyric generation without training on any aligned melody-lyr data.
Outcome: The proposed model generates high-quality lyrics that are singable, intelligible, and coherent than baseline models.
Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models (2025.acl-long)

Copied to clipboard

Challenge: Recent efforts to distill large reasoning models into smaller lightweight models have shown competitive performances.
Approach: They propose to distill long Chain-of-Thought data to improve SFT and RL methods by constructing data from scratch using Monte Carlo Tree Search.
Outcome: The proposed method significantly improves reasoning performance on various benchmarks such as math (GSM8K, MATH, AIME).
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.

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