Papers by Zhan Chen

30 papers
From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are obstructed by their opaque and often unreliable reasoning.
Approach: They propose a framework for trustworthy clinical argumentation by adapting the Toulmin model to the diagnostic process.
Outcome: The proposed method achieves diagnostic accuracy comparable to resource-intensive RL methods while offering a more stable and efficient training pipeline.
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit (2025.acl-long)

Copied to clipboard

Challenge: Existing frameworks for Large Language Models (LLMs) for Click-Through Rate prediction require a careful balance between computational efficiency and predictive accuracy.
Approach: They propose a framework that integrates Retrieval-Augmented Generation with a novel multi-head early exit architecture to address both challenges.
Outcome: The proposed framework reduces retrieval time while maintaining high model performance.
Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction (2026.acl-long)

Copied to clipboard

Challenge: Current distractor generation methods produce shared distractors for all students, ignoring individual variations in reasoning, which limits their diagnostic effectiveness.
Approach: They propose a method which tailors distractors to each student’s specific cognitive flaws, inferred from their past question-answering (QA) history.
Outcome: The proposed framework outperforms existing methods in generating plausible distractors and adapts to group-level settings.
LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluations focus on isolated, short-term interactions, overlooking the inherently long-term nature of learning.
Approach: They propose a benchmark for long-term personalized tutoring based on an annotated learning log . they propose an automated generator–verifier pipeline to enable benchmark expansion .
Outcome: The proposed benchmarks evaluate LLMs across three progressive tasks: evidence acquisition, knowledge state diagnosis, and adaptive teaching action.
Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation metrics struggle to evaluate adversarial negative examples . existing metrics struggle in handling adversarials, resulting in low correlations with human judgments.
Approach: They propose a framework that integrates AMR and domain-specific language models for automatic open-domain dialogue evaluation.
Outcome: The proposed evaluation framework achieves strong correlations with human judgments across multiple datasets.
A Dual-View Analysis of Multiple Languages in Colonial Newspapers (2026.findings-acl)

Copied to clipboard

Challenge: Historical newspapers from the colonial period offer valuable evidence of how racializing language evolved over time.
Approach: They propose a contextual question answering and visual question answering task from colonial newspapers . they propose linguistic training for temporal word embedding with a compass to study racialization .
Outcome: The proposed tasks are limited for low-resource tasks, the authors show . the authors compare the results of two QA pairs from colonial newspapers to a compass .
Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition (2021.naacl-main)

Copied to clipboard

Challenge: Existing knowledge-grounded dialogue models lack fine-grained control over knowledge selection and integration with dialogues.
Approach: They propose to explicitly model the knowledge transition in sequential multi-turn conversations by abstracting knowledge into topic tags.
Outcome: The proposed model outperforms baseline models on knowledge-grounded dialogue benchmarks.
SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation (2024.findings-acl)

Copied to clipboard

Challenge: Existing approaches to evaluate open domain dialogues have a one-to-many problem . existing approaches lack commonsense reasoning biases and perform poorly in domain-specific scenarios.
Approach: They propose a framework that leverages both a small, specialised model and LLMs for the evaluation of open-domain dialogues.
Outcome: The proposed framework achieves state-of-the-art performance in both classification and evaluation tasks and exhibits better correlation with human judgements.
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models.
Approach: They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model.
Outcome: The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD.
Unlocking Black-Box Prompt Tuning Efficiency via Zeroth-Order Optimization (2024.findings-emnlp)

Copied to clipboard

Challenge: Prompt optimization is an important technique for adapting Large Language Models (LLMs) to specific tasks.
Approach: They propose a zeroth-order approach which enables efficient prompt tuning solely via inference APIs.
Outcome: The proposed approach outperforms existing black-box prompt tuning methods in terms of performance and convergence speed.
GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models (2025.findings-acl)

Copied to clipboard

Challenge: Foundation models for single-cell RNA sequencing ignore biological prior knowledge encoded in gene regulatory relationships and fail to leverage multi-omics signals.
Approach: They propose a framework that integrates multi-scale gene regulatory networks into RNA foundation model training.
Outcome: The proposed framework improves on state-of-the-art models on three downstream tasks . it integrates multi-scale gene regulatory networks (GRNs) from multi-omics data into training .
PhyVer: Physics-Grounded Material Claim Verification with Multi-Fidelity Physical Evidence (2026.acl-demo)

Copied to clipboard

Challenge: Existing claim verification pipelines operate over text, producing ungrounded judgments.
Approach: They propose a physics-grounded material claim verification system that can be used to verify claims with physical evidence.
Outcome: The proposed system reduces MAE and sign-offs with experts over text-only GPT-5.1.
Open Set Relation Extraction via Unknown-Aware Training (2023.acl-long)

Copied to clipboard

Challenge: Existing supervised relation extraction methods can still misclassify unknown relations into known relations due to the lack of supervision signals.
Approach: They propose a method that regularizes the model by dynamically synthesizing negative instances that can provide the missing supervision signals.
Outcome: The proposed method achieves SOTA unknown relation detection without compromising the classification of known relations.
Stable Language Guidance for Vision–Language–Action Models (2026.acl-long)

Copied to clipboard

Challenge: Existing vision-Language-Action models are notoriously brittle to linguistic perturbations.
Approach: They propose a probabilistic framework that disentangles physical affordance from semantic execution.
Outcome: The proposed framework disentangles physical affordance from semantic execution.
SLM-Mod: Small Language Models Surpass LLMs at Content Moderation (2025.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are expensive to query in real-time and do not allow for a community-specific approach to content moderation.
Approach: They propose to use small language models for community-specific content moderation tasks by fine-tuning and evaluating their performance against larger open- and closed-sourced models.
Outcome: The proposed models outperform zero-shot LLMs in content moderation tasks with 11.5% higher accuracy and 25.7% higher recall across all communities.
Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning (2025.coling-main)

Copied to clipboard

Challenge: Recent studies have focused on improving the ability of Large Language Models to perform complex reasoning.
Approach: They propose a Direct-Indirect Reasoning method that integrates DR and IR as parallel reasoning paths that are merged to derive the final answer.
Outcome: The proposed method outperforms existing methods on four datasets related to logical reasoning and proof.
DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Copied to clipboard

Challenge: Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach: They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome: The proposed model outperforms baselines on three real-world datasets.
Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge (2025.findings-acl)

Copied to clipboard

Challenge: Temporal Logic (STL) is a formal specification tool for cyber-physical systems . but it is difficult to transform ambiguous and complex data into STL, a paper argues .
Approach: They propose a NL-STL dataset with 16,000 samples enriched with diverse patterns . they propose KGST framework to transform natural language into STL using a generate-then-refine process .
Outcome: The proposed dataset outperforms baseline models in diversity and accuracy . the proposed dataset contains 16,000 samples enriched with diverse patterns .
Uncertainty-Aware Contrastive Sentence Embedding With Local Context Representation for Text Classification (2026.findings-acl)

Copied to clipboard

Challenge: Existing models for text classification are based on encoder-only transformers and generative pre-trained transformers.
Approach: They propose an uncertainty-aware contrastive sentence embedding approach that addresses language ambiguity and inter-class separability for a text classification task.
Outcome: The proposed approach improves classification accuracy on public datasets compared with state-of-the-art methods.
PwnGPT: Automatic Exploit Generation Based on Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Automated exploit generation (AEG) is the automatic discovery and exploitation of vulnerabilities against unknown targets.
Approach: They propose an automatic exploit generation framework that automatically solves pwn challenges by using large language models.
Outcome: The proposed framework improves the completion rate of exploits on the openAI o1-preview model and the GPT-4o model.
Playing 20 Question Game with Policy-Based Reinforcement Learning (D18-1)

Copied to clipboard

Challenge: The 20 Questions (Q20) game encourages deductive reasoning and creativity.
Approach: They propose a policy-based Reinforcement Learning method which learns optimal question selection . the method is robust to noisy answers and uses a reward network to estimate the more informative reward .
Outcome: The proposed method outperforms an entropy-based engineering system and has competitive performance in noisy-free simulation environment.
Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for audio captioning lack fine-grained detail and contextual accuracy due to limited unimodal or superficial information.
Approach: They propose a two-stage automated pipeline that uses pretrained models to extract contextual cues from video . a large language model synthesizes these inputs to generate detailed and context-aware captions .
Outcome: The proposed method is scalable and generates detailed and context-aware captions on large-scale audio datasets.
Beyond the Context Window: Scaling Agentic RL via End-to-end Optimized Context Compression (2026.acl-long)

Copied to clipboard

Challenge: Existing reinforcement learning pipelines suffer from degraded instruction following, excessive rollout costs, and strict context limits.
Approach: They propose a reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use where context length quickly becomes a bottleneck.
Outcome: The proposed framework improves the success rate while maintaining the same or even lower working context length compared to baselines.
MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to improve efficiency often enforce rigid structural constraints such as local attention windows.
Approach: They propose a framework that augments sparse-attention mechanisms with dynamically integrated in-context information through an efficient retrieval system.
Outcome: Empirical results show that MATCH significantly improves the performance of sparse-attention models on synthetic and real-world natural-language tasks.
From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding (2026.acl-long)

Copied to clipboard

Challenge: Existing models for visual information extraction suffer from limitations in scale and realism . ReceiptBench is a large-scale, human-annotated benchmark for receipts .
Approach: They propose a large-scale, human-annotated benchmark for visual information extraction . the method organizes information extraction into four hierarchical sub-tasks .
Outcome: The proposed method surpasses proprietary models on complex reasoning tasks.
History-Aware Conversational Dense Retrieval (2024.findings-acl)

Copied to clipboard

Challenge: Current approaches for conversational dense retrieval rely on fine-tuning a pre-trained ad-hoc retriever, which can be lengthy and noisy.
Approach: They propose a context-denoised query reformulation and automatic mining of supervision signals based on historical turns.
Outcome: The proposed system improves on two public conversational search datasets.
Effectiveness of Pre-training for Few-shot Intent Classification (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing paradigms further pre-train language models such as BERT on vast amount of unlabeled corpus, but we find it highly effective and efficient to simply fine-tune BERT with roughly 1,000 labeled utterances from public datasets.
Approach: They propose to fine-tune BERT with a small set of labeled utterances from public datasets to achieve a pre-trained model based on a set of 1,000 labeles.
Outcome: The proposed model can outperform existing models on domains with very different semantics on novel domains.
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance.
Approach: They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents.
Outcome: The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain.
MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches for content moderation require a separate model for every community and are opaque in their decision-making.
Approach: They propose a modular framework that adds post-hoc explanations to enable scalable content moderation.
Outcome: The proposed framework yields scalable, transparent moderation without fine-tuning across domains.
CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to knowledge-grounded dialogue generation perform relatively independent sub-tasks . Typical approaches tend to decompose this task into two streamlined sub- tasks .
Approach: They propose a collaborative latent variable model to integrate knowledge selection and knowledge-aware response generation simultaneously in separate but collaborative latences.
Outcome: The proposed model outperforms previous methods on knowledge selection and response generation.

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