Papers by Shuyang Zhang

9 papers
Miner: Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models (2026.acl-long)

Copied to clipboard

Challenge: Current critic-free RL methods for large reasoning models suffer from severe inefficiency when training on positive homogeneous prompts.
Approach: They propose a method that repurposes the policy’s intrinsic uncertainty as a self-supervised reward signal, with no external supervision, auxiliary models, or additional inference cost.
Outcome: Evaluated across six reasoning benchmarks on Qwen3-4B and Qwend3-8B base models, the proposed method achieves state-of-the-art performance among the other four methods.
Adaptive Prompt Optimization for Open-Ended Tasks: Uncertainty Preference as a Secondary Signal (2026.findings-acl)

Copied to clipboard

Challenge: Recent training-free prompt optimizers treat performance as maximizing a single scalar score and ignore a second signal that the desired style is task dependent.
Approach: They propose a semantic-entropy-based method that uses task uncertainty to guide prompt optimization by selecting high-entropicy candidates for creative tasks and low-energetic candidates for conservative ones.
Outcome: The proposed method outperforms baselines on MT-Bench subsets and integrates easily into existing prompt optimizers.
BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics (2023.acl-long)

Copied to clipboard

Challenge: Existing benchmarks measure the correlation with human judgements of faithfulness on model-generated summaries, but they are insufficient for diagnosing whether metrics are consistent, effective on human-written texts, and sensitive to different error types.
Approach: They propose to use unfaithful minimal pairs to measure the consistency of automatic faithfulness metrics by comparing human-written summary pairs with a dataset of 889 human-writing, minimally different summary pairs.
Outcome: The proposed benchmarks show that the most discriminative metrics tend not to be the most consistent, and that the best performing metrics are sensitive to errors.
EpiGEN: An Efficient Multi-Api Code GENeration Framework under Enterprise Scenario (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to large language models fail to meet expectations for code generation tasks . existing approaches are faced with drawbacks of high resource consumption and inadequate handling of multi-API tasks.
Approach: They propose an Efficient multi-Api code GENeration framework that uses private APIs to pre-train LLMs.
Outcome: The proposed framework shows good acceptability and readability on single-GPU tasks compared to fully fine-tuned LLMs with a larger number of parameters.
Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer (2025.acl-long)

Copied to clipboard

Challenge: Foundational models and their checkpoints have advanced deep learning, boosting performance across applications.
Approach: They propose a method for pruning fine-tuned models by calculating differences between them and original model.
Outcome: The proposed method can improve performance across vision, NLP, and multi-modal benchmarks.
SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks have highlighted character-level tasks as lacking practical relevance . many real-world applications rely heavily on precise sub-token understanding .
Approach: They propose a benchmark that assesses sub-token understanding through practical tasks . they examine the impact of test-time scaling on sub-word reasoning .
Outcome: The proposed benchmark assesses sub-token understanding through practical tasks . it includes ten tasks across four domains and isolates tokenization-related failures .
Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to enhance medical reasoning lack high-quality data.
Approach: They propose a medical knowledge-enhanced data Synthesis and Semi-supervised Reinforcement learning framework that uses rare disease knowledge to synthesize distribution-controllable reasoning questions.
Outcome: The proposed method outperforms existing methods across ten medical benchmarks and achieves up to 5.93% gain on rare diseases tasks.
HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance (2026.findings-acl)

Copied to clipboard

Challenge: Low-Rank Adaptation (LoRA) assumes a uniform rank r for each incremental matrix, not accounting for the varying significance of weight matrices across modules and layers.
Approach: They propose a framework that allows for faster convergence of low-rank adaptive models . they use a hypernetwork to prune the outputs of the hypernetworks to generate parameters .
Outcome: The proposed framework accelerates convergence of AdaLoRA by leveraging a hypernetwork.
To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Merging (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to model merging ignore the fundamental roles of neurons, connectivity and activation.
Approach: They propose a framework that relies on neuronal mechanisms to mitigate task interference . they decomposed task-specific representations into two complementary subspaces . their results offer new insights into mitigating task interference and improving knowledge fusion .
Outcome: The proposed framework reduces task interference within neurons and improves knowledge fusion.

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