Papers by Hongyi Li

16 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.
STREAM-ZH: Simplified Topic Retrieval Exploration and Analysis Module for Chinese Language (2026.eacl-short)

Copied to clipboard

Challenge: Simplified Topic Retrieval Exploration and Analysis Module for Chinese language is the first topic modeling package to fully support the Chinese language.
Approach: They propose a topic modeling package that fully supports the Chinese language . they use preprocessed textual datasets to assess topic models .
Outcome: The proposed framework outperforms existing topic models using English-translated textual input.
Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing GEC datasets in Chinese fail to consider specific grammatical error types and overlook cross-sentence grammamatical errors.
Approach: They propose to use Chinese essay fluency assessment to assess essay fluencies along with coarse and fine-grained errors and corrections to improve explainability.
Outcome: The proposed dataset encapsulates essay fluency scores along with both coarse and fine-grained errors and corrections.
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Copied to clipboard

Challenge: Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach: AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome: Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .
EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing language model agents excel in planning and reasoning, but lack creativity in unfamiliar environments.
Approach: They propose a benchmark suite of room escape game environments to challenge agents with creative reasoning, unconventional tool use and iterative problem-solving to uncover implicit goals.
Outcome: The proposed framework can perform with 40% fewer steps and hints and performs robustly across difficulty levels.
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches (2024.findings-emnlp)

Copied to clipboard

Challenge: Long context capability is a crucial competency for large language models as it mitigates the human struggle to digest long-form texts.
Approach: They propose to evaluate 10+ state-of-the-art approaches for long context-capable LLMs.
Outcome: The proposed methods are compared against 10+ state-of-the-art approaches across seven categories of long context tasks.
Rubrik’s Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset (2025.acl-long)

Copied to clipboard

Challenge: Large-Language Models (LLMs) are increasingly being used in explanation generation tasks due to their unreliability.
Approach: They propose a rubric and a dataset of 26k explanations written and quality-annotated using the rubric by humans and six open- and closed-source LLMs to test their proposed rubric.
Outcome: The proposed rubric and CUBE dataset focuses on reasoning and language tasks and provides the necessary diversity to test it.
MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning (2024.acl-long)

Copied to clipboard

Challenge: In math reasoning with large language models, fine-tuning data augmentation by query evolution and diverse reasoning paths is empirically verified effective.
Approach: They propose to fine-tune data augmentation by query evolution and diverse reasoning paths.
Outcome: The proposed model achieves new state-of-the-art on GSM8K and MATH.
Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)

Copied to clipboard

Challenge: Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values.
Approach: They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent.
Outcome: The proposed method improves on a two-agent game with an adversarial agent and a defensive agent.
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition (2024.acl-long)

Copied to clipboard

Challenge: supervised fine-tuning (SFT) is a technique used to enhance multiple abilities in large language models.
Approach: They propose to study the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning.
Outcome: The proposed model improves math reasoning and code generation with increasing data amount . the proposed model size and SFT strategies can be used to learn multiple skills with different scaling patterns.
Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis (2024.findings-naacl)

Copied to clipboard

Challenge: Existing studies show that large language models (LLMs) can handle multilingual machine translation (MMT) However, the multilingual translation ability of LLMs remains under-explored.
Approach: They evaluate eight popular LLMs including ChatGPT and GPT-4 to determine their performance in multilingual machine translation.
Outcome: The proposed model can generate moderate translation even on zero-resource languages and cross-lingual exemplars can provide better task guidance for low-resourced translation than exemplar in the same language pairs.
LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem (2025.findings-emnlp)

Copied to clipboard

Challenge: distributing LLMs without a proven track record like ‘meta-llama‘ or ‘qwen‘ rarely gains community traction.
Approach: They propose a simple, efficient, yet specific recipe for a backdoor LoRA to be injected into task-enhancing LoRAs and examine the mechanisms of such infections.
Outcome: The proposed model allows attackers to scale the distribution of compromised LoRAs with minimal effort by leveraging the rich pool of shared LoRA assets.
Selective Prefix Tuning for Pre-trained Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for fine-tuning pre-trained models are time-consuming and memory-inefficient.
Approach: They propose a method that inserts learnable vectors into each Transformer layer . they propose SL to encourage diversity in prefix tokens .
Outcome: Extensive experiments validate the effectiveness of Prefix Tuning in sentence and token classification tasks.
EMA: An Episodic Memory Agent for Efficient and Selective Memory (2026.findings-acl)

Copied to clipboard

Challenge: Existing memory-augmented methods often incorporate full dialog histories without filtering, resulting in information redundancy and inference latency.
Approach: They propose a framework that abstracts conversational context into Episodic Memory Units (EMUs) they propose EMA, MemDecider and a filtering decision module to reduce noise and improve overall performance.
Outcome: The proposed framework reduces token consumption by 11.48% while improving performance on two widely-used benchmarks.
Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning (2025.findings-emnlp)

Copied to clipboard

Challenge: Low-Confidence Gold (LCG) is a new filtering framework for Large Language Models that curates high-quality subsets while preserving data diversity.
Approach: They propose a new filtering framework that employs centroid-based clustering and confidence-guided selection for identifying valuable instruction pairs.
Outcome: The proposed framework improves performance on a subset of 6K samples while maintaining data diversity.
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users (2025.findings-emnlp)

Copied to clipboard

Challenge: Retrieval-augmented generation is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations.
Approach: They propose a practical three-level threat model from the perspective of user fairness awareness.
Outcome: The proposed model shows that RAG can undermine fairness alignment without fine-tuning or retraining.

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