Papers by Yan Pan

24 papers
Towards Explainable Computerized Adaptive Testing with Large Language Model (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods focus on minimizing the number of questions required to assess ability, lacking clear and reliable explanations for the question selection process.
Approach: They propose to use large language models to enhance computer adaptive testing (CAT) by providing human-like interpretability and explanations.
Outcome: The proposed agent-based CAT performs comparably or superior to traditional CAT methods in accuracy and significantly improves student trust and satisfaction.
DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have emerged as prominent foundation models for diverse applications due to their outstanding ability to understand and generate humanlike text.
Approach: They propose a dynamic decision-making framework that categorizes tasks into two distinct pathways: 'Fast' and 'Slow' they propose 'self-consistency' strategy to replace the straight-forward decoding method used in COT prompting .
Outcome: The proposed method achieves more than 3% increase in accuracy with lower cost on five popular reasoning benchmarks.
Cool-Fusion: Fuse Large Language Models without Training (2025.acl-long)

Copied to clipboard

Challenge: Cool-Fusion is a simple yet effective approach to combine two or more heterogeneous large language models .
Approach: They propose a method that fuses the knowledge of two or more heterogeneous large language models to leverage complementary strengths.
Outcome: The proposed method increases accuracy from three strong source LLMs on GSM8K by 17.4%.
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are stateless and limited by a finite context window, preventing them from maintaining knowledge across long conversations or evolving tasks.
Approach: They propose a reinforcement learning framework that empowers LLMs to actively manage external memory through two specialized agents.
Outcome: The proposed framework outperforms baselines and benchmarks across diverse question types, three benchmarks, and multiple model scales.
MMedAgent: Learning to Use Medical Tools with Multi-modal Agent (2024.findings-emnlp)

Copied to clipboard

Challenge: Multi-modal Large Language Models (MLLMs) exhibit limited generality and often fall short when compared to specialized models.
Approach: They propose a multi-modal medical agent that picks the most suitable medical tools based on user inputs.
Outcome: The proposed agent performs better than open-source models and the closed-source model, GPT-4o.
MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing RAG systems struggle with the quality of retrieval documents, causing performance degradation and reducing performance.
Approach: They propose a training-free RAG framework that leverages multiple LLM agents to collaboratively filter and score retrieved documents.
Outcome: The proposed framework outperforms existing RAG frameworks in QA benchmarks and shows superior answer consistency and answer accuracy over baseline methods.
Enhancing Foundation Models in Transaction Understanding with LLM-based Sentence Embeddings (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing foundation models for tabular transactional data rely on index-based representations for categorical merchant fields.
Approach: They propose a framework that uses LLM-generated embeddings as semantic initializations for lightweight transaction models.
Outcome: The proposed framework improves performance on large transaction datasets.
Thinking Before You Speak: A Proactive Test-time Scaling Approach (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models often exhibit deficiencies with complex reasoning tasks, such as maths, due to the discrepancy between human reasoning patterns and those presented in training data.
Approach: They propose to insert insights between consecutive reasoning steps to bridge this gap by generating insights between the next reasoning steps.
Outcome: Experiments on mathematical datasets confirm the effectiveness of the proposed reasoning framework on complex problems.
CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026.acl-long)

Copied to clipboard

Challenge: Label-free reinforcement learning enables large language models to improve reasoning capabilities . but as training maximizes self-consistency, output diversity collapses, authors say . authors propose a framework where a single model alternates between generator and verifier roles .
Approach: They propose a framework where a model alternates between generator and verifier roles, bootstrapping each other.
Outcome: Experiments show that CoVerRL outperforms label-free baselines on reasoning benchmarks . the framework can be used to improve reasoning abilities without ground-truth supervision .
ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks (2025.findings-acl)

Copied to clipboard

Challenge: Solving expert-level multimodal tasks requires strong user query understanding, domain-specific knowledge, and advanced reasoning abilities.
Approach: They propose a benchmark of open-ended user queries encapsulating professional expertise and advanced reasoning.
Outcome: The proposed benchmark is publicly accessible at TBC.
Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to text-to-SQL require domain knowledge to parse expert questions into SQL queries.
Approach: They propose a framework to leverage domain knowledge during parsing by building a new benchmark KnowSQL with domain-specific questions.
Outcome: The proposed framework improves the performance of the proposed benchmark by 28.2%.
ASD-iLLM:An Intervention Large Language Model for Autistic Children based on Real Clinical Dialogue Intervention Dataset (2025.findings-emnlp)

Copied to clipboard

Challenge: Currently, leveraging large language models (LLMs) for autism intervention is a significant yet challenging task, especially when directly employing LLMs as an intervention doctor.
Approach: They propose a framework for training LLMs to conduct dialogue interventions in accordance with the principles of Applied Behavior Analysis (ABA) they also propose 'role-play' strategy in which LLM act as autistic children to comprehensively evaluate the doctor model's capabilities at the dialogue level.
Outcome: The proposed framework outperforms existing models in both automatic and human evaluation, with intervention strategies and dialogue style more closely resembling those of clinical intervention doctors.
Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning? (2024.acl-long)

Copied to clipboard

Challenge: Current temporal reasoning datasets are limited to questions about single or isolated events, falling short in mirroring the realistic temporal characteristics involving concurrent nature and intricate temporal interconnections.
Approach: They propose a co-temporal Question Answering benchmark that contains four co-time scenarios with 4,748 samples for evaluating the co-timing abilities of large language models.
Outcome: The proposed benchmarks show that current LLMs struggle on CoTempQA tasks even when enhanced with Chain of Thought methodologies.
Reading Like HER: Human Reading Inspired Extractive Summarization (D19-1)

Copied to clipboard

Challenge: Existing methods for extracting text summarization are abstractive and extractive.
Approach: They propose a novel approach for extractive summarization by simulating two stages . they adopt a convolutional neural network to encode gist of paragraphs for rough reading .
Outcome: The proposed method significantly outperforms the state-of-the-art extractive methods on CNN and DailyMail datasets.
From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement (2025.emnlp-main)

Copied to clipboard

Challenge: Chain-of-Thought reasoning introduces significant inference latency due to its verbosity.
Approach: They propose a framework that leverages token elasticity phenomenon to progressively compress CoTs via multiround refinement.
Outcome: The proposed method achieves an average accuracy improvement of 5.6% over state-of-the-art baselines while reducing CoT length by an average of 47 tokens and significantly lowering latency.
Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing work on rationale quality underestimates the importance of CoT distillation, focusing primarily on data quantity, which may result in transferring noisy or incorrect information to the student model.
Approach: They propose a method which can discern and select high quality rationales for distillation and a Rationale Difficulty metric to measure the ability of the student model to generate the correct answer under a given rationale.
Outcome: The proposed method achieves 4.6% accuracy improvement over baseline data on seven datasets over three tasks, controlling accuracy, diversity, and difficulty.
MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown impressive progress in mathematical problem-solving . current approaches to enhance mathematical reasoning focus on instance-level modifications .
Approach: They propose a framework that enhances mathematical reasoning through cross-problem instruction synthesis.
Outcome: The proposed framework boosts mathematical reasoning by 18.0 points while maintaining high data efficiency.
Improving Open-Domain Dialogue Systems via Multi-Turn Incomplete Utterance Restoration (D19-1)

Copied to clipboard

Challenge: Experimental results show that restoring incomplete utterances from context improves the performance of open-domain dialogue systems.
Approach: They propose to use a dataset to restore incomplete utterances from context . they propose to pick and combine the data to restore the incomplete .
Outcome: The proposed model significantly boosts response quality of open-domain dialogue systems.
Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis (2026.acl-long)

Copied to clipboard

Challenge: Existing models re-encode the sentence for each aspect or rely on static use of deep representations, leading to redundant computation and limited adaptivity.
Approach: They propose a single-pass inference framework that encodes each sentence once to construct a reusable, depth-ordered substrate.
Outcome: Experiments show that DABS reduces end-to-end computation by 60% in multi-aspect settings.
Demystify the Role of Memory in Machine Learning Engineering Agents (2026.findings-acl)

Copied to clipboard

Challenge: Unlike short, reactive exchanges, MLE agents solve tasks through cycles of experimentation and improvement where past errors can inform future success.
Approach: They propose a dynamic coding memory that captures and reuses debugging experiences and integrates it into two representative agent paradigms.
Outcome: The proposed agent model captures and reuses debugging experiences and integrates it into two agent paradigms.
HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Challenge: Current approaches to addressing knowledge outdating in LLMs struggle with retrieval and generation aspects when handling outdated information.
Approach: They propose a benchmark to evaluate the impact of outdated information on RAG . they use token-level diff algorithms and LLM pipelines to create a large-scale QA dataset .
Outcome: The proposed benchmark analyzes the impact of outdated information on RAG performance.
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains.
Approach: They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries.
Outcome: The proposed system outperforms baselines in the open domain task-solving benchmark.
Reward Generalization in RLHF: A Topological Perspective (2025.findings-acl)

Copied to clipboard

Challenge: Existing alignment methods share a common topology of information flow, but their alternatives have not been thoroughly explored.
Approach: They propose a theory of reward generalization in reinforcement learning from human feedback . they propose induced Bayesian networks to model the impact of dataset topologies on reward generalisation .
Outcome: The proposed method achieves an average win rate of 65% on three NLP 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