Papers by Yihong Dong

15 papers
CODERL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models excel at code generation by learning from vast code corpora, but a fundamental semantic gap remains between training on textual patterns and the goal of functional correctness . reinforcement learning with verifiable rewards (RLVR) approaches are inefficient for establishing a well-aligned connection between the textual representation of code and its execution semantics.
Approach: They propose a novel approach that integrates execution semantics alignment into the RLVR training pipeline for code generation.
Outcome: The proposed model outperforms baseline training and RLVR and shows strong applicability across RL and LLMs.
IntentCoding: Amplifying User Intent in Code Generation (2026.findings-acl)

Copied to clipboard

Challenge: IntentCoding captures the influence of user intent by masking out the intent, and integrates seamlessly with existing decoding procedures.
Approach: They propose a decoding strategy that captures the influence of user intent by masking out the intent and applies a multi-strength ensemble mechanism to amplify the effect of user intention during generation.
Outcome: The proposed model significantly improves both constraint satisfaction and functional correctness compared to greedy decoding approaches.
BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition (2025.coling-main)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP) that aims to detect the entity spans of text and classify them into pre-defined set of entity types.
Approach: They propose a boundary-aware contrastive learning strategy to enhance the LLM’s ability to perceive entity boundaries for generalized entity spans.
Outcome: The proposed framework outperforms prior methods and validates its effectiveness across a range of LLM architectures.
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach: They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome: The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.
PACE: Improving Prompt with Actor-Critic Editing for Large Language Model (2024.findings-acl)

Copied to clipboard

Challenge: Prompt with Actor-Critic Editing (PACE) for LLMs improves performance of different human-written prompts, resulting in significant performance discrepancies.
Approach: They propose to use LLMs as actors and critics to enable automatic prompt editing by taking feedback from both actors performing prompt and criticizing response into account.
Outcome: The proposed model improves the performance of human-written prompts by 98% and compares to high-quality human-writing prompts.
LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs (2025.acl-long)

Copied to clipboard

Challenge: TrickCatcher generates test cases that pass existing tests yet contain bugs . a recent study found that tricky bugs are not detected by test suites .
Approach: They propose an LLM-powered approach to generating test cases for uncovering bugs in plausible programs . they use a PUT and specification to generate program variants, an input generator and an Llm to construct test inputs .
Outcome: The proposed approach achieves recall, precision, and F1 scores that are 1.80, 2.65, and 1.66 . trickCatcher generates program variants based on the program under test and its specification .
Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points (2025.findings-acl)

Copied to clipboard

Challenge: Current code generation models produce errors concentrated at specific error-prone points, affecting accuracy of code.
Approach: They propose a framework that focuses preference optimization on error-prone areas . focused-DPO improves the accuracy and reliability of code generation by reducing common errors .
Outcome: The proposed framework improves code generation by focusing on error-prone areas.
Saber: Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model in Code Generation (2026.acl-long)

Copied to clipboard

Challenge: Diffusion language models (DLMs) offer advantages in parallel generation and bidirectional context modeling, but they face a critical trade-off between inference speed and output quality for tasks with strict structural constraints such as code generation.
Approach: They propose an efficient sampling algorithm that reduces the number of tokens unmasked per step based on the model’s evolving confidence.
Outcome: The proposed method improves Pass@1 accuracy by 1.9% while achieving 251.4% inference speedup.
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning for LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to reinforcement learning with verifiable reward (RLVR) are limited by difficulty or lack of exploration.
Approach: They propose a self-evolving curriculum learning framework based on chain-of-thought reasoning optimization that constrains exploration space by self-generating and verifying CoT trajectories.
Outcome: The proposed framework enables LLMs to solve previously unsolved problems without external supervision and is compatible with various RL fine-tuning methods.
Rethinking Repetition Problems of LLMs in Code Generation (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have focused on content repetition, but structural repetition is a more prevalent problem in code generation.
Approach: They propose a decoding approach that eliminates repetition problems in code generation by identifying grammar rules and strategically decaying the likelihood of critical tokens that contribute to repetitions.
Outcome: The proposed approach outperforms baselines and humanEval benchmarks on CodeRepetEval dataset and MBPP benchmarks, effectively reducing repetitions and enhancing the quality of generated code.
SuLoRA: Subspace Low-Rank Adaptation for Parameter-Efficient Fine-Tuning (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for fine-tuning large language models (LLMs) introduce parameter interference, leading to a gap in generalization performance for specific tasks compared to full fine-uning.
Approach: They propose a parameter-separated low-rank adapter to account for task differences by decomposing LoRA’s parameter matrix into multiple independent subspaces and assigning them differentially to distinct tasks.
Outcome: The proposed method outperforms LoRA in trainable parameter efficiency and overall model performance on various NLP tasks.
Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Considering the vast size and wide-ranging sources of LLMs’ training data, it could explicitly or implicitly include test data.
Approach: They propose a Contamination Detection via output Distribution (CDD) which detects data contamination only by identifying the peakedness of LLM's output distribution.
Outcome: The proposed method improves performance by 21.8%-30.2% on humanEval and TED: trustworthy evaluation via output distribution.
KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development? (2026.acl-long)

Copied to clipboard

Challenge: Existing domain-specific code benchmarks focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge.
Approach: They propose a benchmark to evaluate domain specialization methods in real-world software development.
Outcome: KOCO-bench is a new benchmark for evaluating domain specialization methods in real-world software development.
CodeDPO: Aligning Code Models with Self Generated and Verified Source Code (2025.acl-long)

Copied to clipboard

Challenge: Existing training methods for code generation do not improve code correctness and efficiency.
Approach: They propose a framework that integrates preference learning into code generation to improve code correctness and efficiency.
Outcome: The proposed framework improves code correctness and efficiency by integrating preference learning into code generation.
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026.acl-long)

Copied to clipboard

Challenge: Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs).
Approach: They propose a hybrid-policy optimization approach that synergizes internal exploitation with external data to achieve stronger reasoning capabilities.
Outcome: The proposed approach achieves state-of-the-art performance on six math reasoning benchmarks and superior performance on out-of distribution reasoning tasks.

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