Papers by Yuchen Ma

17 papers
Tree-of-Evolution: Tree-Structured Instruction Evolution for Code Generation in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Data synthesis is a key research area in large language models (LLMs).
Approach: They propose a framework that models code instruction synthesis process with a tree structure and optimization-driven evolution to alleviate constraints of unidirectional synthesis and randomness-driven generation.
Outcome: The proposed framework outperforms open-weight code LLMs on five widely-used benchmarks.
TC–RAG: Turing–Complete RAG’s Case study on Medical LLM Systems (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to RAG neglect system state variables, resulting in poor performance and erroneous knowledge accumulation.
Approach: They propose a framework that incorporates a Turing Complete System to manage state variables and manage retrieval halting.
Outcome: The proposed framework improves on seven real-world healthcare datasets and shows that it is more accurate than existing methods.
CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding? (2025.coling-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have showcased impressive code generation capabilities, primarily evaluated through language-to-code benchmarks.
Approach: They propose a benchmark to assess LLMs’ code understanding abilities from the perspective of code judging rather than code generation.
Outcome: The proposed benchmark evaluates 12 well-known large language models to determine the correctness of provided code solutions.
On Fake News Detection with LLM Enhanced Semantics Mining (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for detecting fake news use only news embeddings to capture the lexical semantics between tokens.
Approach: They propose a topic-based model with prompts to extract news embeddings from LLMs and a generalized page-rank model to extract local and global semantics.
Outcome: The proposed model shows superior performance on five benchmark datasets over seven baseline methods.
MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for Large Multimodal Models (LMMs) are constrained by static representations, inadequately evaluating their ability to understand time-sensitive knowledge.
Approach: They propose a benchmark containing 2,104 time-sensitive knowledge samples spanning six knowledge types to evaluate temporal awareness along 6 key dimensions and 11 challenging tasks.
Outcome: The proposed benchmark measures temporal awareness along 6 key dimensions and 11 tasks, while most open-source LMMs still lack time understanding ability.
Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach: They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome: The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .
M3-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge-based VQA benchmarks focus on coarse-grained categories and simple reasoning over single entities.
Approach: They propose a knowledge-based Visual Question Answering benchmark to enhance multimodality evaluation.
Outcome: The proposed benchmark improves evaluation of multimodal large language models in fine-grained multimodal entity understanding and complex multihop reasoning.
SciVQR: A Multidisciplinary Multimodal Benchmark for Advanced Scientific Reasoning Evaluation (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for multimodal large language models fail to capture complexity and traceability of reasoning processes . SciVQR includes domain-specific visuals and challenges models to combine visual comprehension with reasoning.
Approach: They propose a multimodal benchmark for scientific reasoning covering 54 subfields . SciVQR includes domain-specific visuals and challenges models to combine visual comprehension with reasoning .
Outcome: SciVQR evaluates 54 subfields in mathematics, physics, chemistry, geography, astronomy, and biology . the results highlight the need for improved multi-step reasoning and integration of interdisciplinary knowledge .
ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability (2026.acl-long)

Copied to clipboard

Challenge: Existing rerankers perform poorly in complex ranking scenarios due to the scarcity of reasoning-intensive training data.
Approach: They propose an automated reasoning-intensive training framework which generates high-quality training labels from training queries and passages.
Outcome: The proposed model outperforms baselines significantly and achieves much lower latency than the pointwise reranker.
Agentic-R: Learning to Retrieve for Agentic Search (2026.findings-acl)

Copied to clipboard

Challenge: Existing retrievers for single-turn retrieval-augmented generation (RAG) rely on similarity-based retrievers, but similar passages are not always useful for final answer generation.
Approach: They propose a retrieval-augmented-generation retriever that integrates reasoning with retrieval . they use local query-passage relevance and global answer correctness to measure passage utility .
Outcome: The proposed retriever outperforms existing retrievers on QA benchmarks on seven single-hop and multi-hop searches.
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to formalizing mathematical statements face limitations in accuracy, especially in the context of complex, highlevel problems that involve sophisticated mathematical reasoning.
Approach: They propose a CriticLean framework that elevates the role of the critic from a passive validator to an active learning component and introduce a benchmark to measure models’ ability to distinguish semantically correct from incorrect formalizations.
Outcome: The proposed framework outperforms open- and closed-source benchmarks and shows that it significantly outperformed existing models.
MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique (2025.findings-emnlp)

Copied to clipboard

Challenge: e MM-CRITIC is a holistic benchmark for evaluating the critique ability of Large Multimodal Models (LMMs) covering 8 main task types and over 500 tasks, covering 4471 samples.
Approach: They introduce a holistic benchmark for evaluating the critique ability of Large Multimodal Models across multiple dimensions: basic, correction, and comparison.
Outcome: The proposed benchmark covers 8 main task types and over 500 tasks and is composed of 4471 samples.
BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation (2022.naacl-main)

Copied to clipboard

Challenge: Standard evaluation metrics, e.g., BLEU, TER and METEOR, focus on the quality of translations at the sentence level and do not consider discourse-level features.
Approach: They propose to use a metric to take discourse coherence into consideration by categorizing discourse-related spans and calculating the similarity-based F1 measure of categorized spans.
Outcome: The proposed metric possesses better selectivity and interpretability at the document-level, and is more sensitive to document- level nuances.
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026.acl-long)

Copied to clipboard

Challenge: Unified Multimodal Models have achieved remarkable success in cross-modal comprehension, but a gap persists in their ability to translate internal knowledge into faithful and controllable synthesis.
Approach: They propose a self-improvement framework that partitions a single UMM into three collaborative roles: Proposer, Solver, and Judge.
Outcome: The proposed framework improves on TIIF, DPG, CompBench and UniCycle benchmarks.
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for dataset poisoning require full-dataset poison, which breaks code compilability.
Approach: They propose a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths.
Outcome: The proposed method contaminates 10% of the dataset while maintaining 100% compilability and functional correctness.
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs)-based agents have fundamentally reshaped artificial intelligence . however, the inherent statelessness of LLMs hinders their ability to maintain logical consistency across complex, multi-step tasks .
Approach: They propose a framework for LLM agent memory mechanisms that formalizes the development process into three stages: storage, reflection, and experience.
Outcome: The proposed framework breaks the development process into three stages . it analyzes the need for long-range consistency, challenges in dynamic environments, and the ultimate goal of continual learning.
MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems (2024.findings-emnlp)

Copied to clipboard

Challenge: Programming often involves translating detailed and complex specifications into code . current state-of-the-art models struggle to solve these problems, a new study shows .
Approach: They propose a multi-modal coding dataset to evaluate algorithmic problem-solving skills in visually rich contexts.
Outcome: The proposed model lacks powerful vision-code models due to the extreme demand for reasoning abilities.

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