Papers by Feng Nan

23 papers
End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches for synthetic QA data generation have limited or no success in improving the downstream Reading Comprehension task.
Approach: They propose an end-to-end approach for synthetic QA data generation using a transformer-based encoder-decoder network that is trained end- to-end to generate both answers and questions.
Outcome: The proposed model outperforms current state-of-the-art methods in the domain adaptation of QA models.
Dual-Channel Evidence Fusion for Fact Verification over Texts and Tables (2022.naacl-main)

Copied to clipboard

Challenge: Existing fact extraction and verification tasks only consider evidence of a single format . Existing models convert evidence into either sentences or tables, thus losing context information .
Approach: They propose a Dual Channel Unified Format fact verification model which unifies various evidence into parallel streams, i.e., natural language sentences and a global evidence table, simultaneously.
Outcome: The proposed model outperforms existing models in two formats by a large margin . it makes the most of existing tables and tables to absorb evidence of two formats .
Topic Modeling with Wasserstein Autoencoders (P19-1)

Copied to clipboard

Challenge: Existing probabilistic topic models are based on latent Dirichlet allocations and collapsed Gibbs sampling.
Approach: They propose a novel topic model that enforces Dirichlet prior on latent document-topic vectors and a kernel kernel to minimize the Maximum Mean Discrepancy (MMD) They propose to measure the diversity of the produced topics and to use the widely used coherence measure NPMI to evaluate topic quality.
Outcome: The proposed model performs better than existing topic models on real datasets.
UnifEE: Unified Evidence Extraction for Fact Verification (2023.eacl-main)

Copied to clipboard

Challenge: Existing models extract evidence in both sentences and table cells from Wikipedia dumps, ignoring potential connections between them.
Approach: They propose a model which uses a mixed evidence graph to extract the evidence in both formats without manually designed conversion rules.
Outcome: The proposed model outperforms existing models and improves the verification step.
Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction (2021.acl-long)

Copied to clipboard

Challenge: Open-domain question answering is a task to answer questions using passages with diverse topics.
Approach: They propose a model that aggregates evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions.
Outcome: The proposed model achieves state-of-the-art performance on AmbigQA dataset and shows competitive performance on NQ-Open and TriviaQA.
Examining False Positives under Inference Scaling for Mathematical Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in language models have led to significant improvements in mathematical reasoning across benchmarks.
Approach: They analyze the prevalence of false positives in language models by using heuristic evaluation methods . they find that false positive models produce correct final answers but with flawed deduction paths .
Outcome: The proposed model performance improvements are based on the proposed model and its evaluation metrics.
Entity-level Factual Consistency of Abstractive Text Summarization (2021.eacl-main)

Copied to clipboard

Challenge: Existing models exhibit entity hallucination, generating names of entities that are not present in the source document.
Approach: They propose to use entity-level factual consistency to improve model quality . they propose to filter the training data to reduce entity hallucination problem .
Outcome: The proposed model can reduce the entity hallucination problem by filtering the training data.
Enhancing Structured Evidence Extraction for Fact Verification (2023.emnlp-main)

Copied to clipboard

Challenge: Open-domain fact verification requires extracting and integrating both structured and unstructured evidence to verify a claim.
Approach: They propose a method to enhance the extraction of structured evidence by leveraging the row and column semantics of tables.
Outcome: The proposed method achieves evidence recall of 60.01% on the test set, higher than the previous state-of-the-art method.
Margin-aware Unsupervised Domain Adaptation for Cross-lingual Text Labeling (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to learn a model from labeled data are expensive or prohibitive.
Approach: They propose an unsupervised domain adaptation algorithm that leverages labeled data in a source domain to learn a well-performing model in . they use the Margin Disparity Discrepancy algorithm to optimize the margin loss on the source domain.
Outcome: The proposed approach improves on a recent theoretical work on cross-lingual document classification and NER by a large margin.
Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization (2023.findings-eacl)

Copied to clipboard

Challenge: Abstractive summarization models generate fluent and well-formed output but lack semantic faithfulness, or factuality, with respect to the input documents.
Approach: They propose new factuality metrics that adjust for the degree of abstractiveness . they propose to visualize the rates of change in factual as we gradually increase abstractiveity .
Outcome: The proposed models generate fluent and well-formed summaries but lack semantic faithfulness, or factuality, with respect to the input documents.
MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains (2025.findings-naacl)

Copied to clipboard

Challenge: Existing benchmarks focus on specific application scenarios, emphasizing task completion but failing to dissect the underlying skills that drive these outcomes.
Approach: They propose a Massive Multitask Agent Understanding benchmark that evaluates LLMs across five domains and offline tasks.
Outcome: The Massive Multitask Agent Understanding (MMAU) benchmark evaluates models across five domains including Tool-use, Directed Acyclic Graph (DAG) QA, Data Science and Machine Learning coding, Contest-level programming and Mathematics.
Harder Task Needs More Experts: Dynamic Routing in MoE Models (2024.acl-long)

Copied to clipboard

Challenge: Unlike existing MoE approaches that rely on fixed TopK Routing, our dynamic expert selection framework dynamically allocates experts based on the confidence level in expert selection for each input.
Approach: They propose a dynamic expert selection framework that dynamically allocates experts based on the confidence level in expert selection for each input.
Outcome: The proposed method achieves an average improvement of 0.7% with less than 90% activated parameters and outperforms dense models in QA and machine translation tasks.
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.
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities (2025.findings-naacl)

Copied to clipboard

Challenge: Recent advances in large language models have led to a growing interest in tool assisted LLMs . toolSandbox includes stateful tool execution, implicit state dependencies between tools .
Approach: a new tool-based evaluation tool is released to help LLMs evaluate their tool-use capabilities. a tool-driven evaluation tool includes stateful tool execution, implicit state dependencies between tools and a built-in user simulator.
Outcome: the toolSandbox evaluation benchmark shows that open source and proprietary models have a performance gap . the benchmarks show that even the most capable LLMs are challenged by state dependent tasks .
CodeBERT: A Pre-Trained Model for Programming and Natural Languages (2020.findings-emnlp)

Copied to clipboard

Challenge: Large pre-trained models have improved performance on a variety of natural language processing tasks.
Approach: They develop a bimodal pre-trained model for programming language (PL) and natural language (NL) it incorporates a hybrid objective function that detects replaced tokens from generators.
Outcome: The proposed model performs better on two NL-PL applications by fine-tuning model parameters.
Semantic Parsing with Syntax- and Table-Aware SQL Generation (P18-1)

Copied to clipboard

Challenge: Existing approaches generate a SQL query word-by-word but results are incorrect or not executable due to mismatch between question words and table contents.
Approach: They propose a generative model to map natural language questions into SQL queries.
Outcome: The proposed model significantly improves state-of-the-art execution accuracy from 69.0% to 74.4% on a large question- SQL dataset.
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach: They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome: The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.
Supporting Clustering with Contrastive Learning (2021.naacl-main)

Copied to clipboard

Challenge: Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space, but different categories overlap with each other at the beginning of the learning process.
Approach: They propose a framework to leverage contrastive learning to promote better separation between different categories by optimizing a clustering objective defined in the representation space.
Outcome: The proposed framework improves state-of-the-art accuracy and normalized mutual information on short text clustering and combines top-down and bottom-up instance discrimination to achieve better distances.
LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for fact checking textual statements are not yet available.
Approach: They propose a neural network approach capable of leveraging logical operations for fact checking . they use a textual statement and semi-structured tables to generate a program from it .
Outcome: The proposed approach achieves state-of-the-art performance on TABFACT dataset . it derives a program (a.k.a. logical form) of the statement in semantic parsing manner .
Improving Factual Consistency of Abstractive Summarization via Question Answering (2021.acl-long)

Copied to clipboard

Challenge: Recent studies show that about 30% of summaries generated by neural text summarization suffer from fact fabrication.
Approach: They propose an automatic evaluation metric to measure factual consistency and a learning algorithm that maximizes the metric during model training.
Outcome: The proposed method improves factual consistency and overall quality of summarization models.
SWING: Balancing Coverage and Faithfulness for Dialogue Summarization (2023.findings-eacl)

Copied to clipboard

Challenge: Existing approaches to dialogue summarization rely on features of conversation data.
Approach: They propose to use natural language inference models to improve coverage and faithfulness . they use fine-grained training signals to encourage model to generate missing content .
Outcome: The proposed model achieves higher faithfulness and coverage while maintaining conciseness compared to prior methods.
ContraCLM: Contrastive Learning For Causal Language Model (2023.acl-long)

Copied to clipboard

Challenge: Existing studies show that causal language models lack expressiveness due to poor discrimination ability.
Approach: They propose a contrastive learning framework that enhances discrimination of representations and bridges the gap with encoder-only models.
Outcome: The proposed framework improves discrimination and source code generation capabilities on a variety of downstream tasks.
Using Structured Content Plans for Fine-grained Syntactic Control in Pretrained Language Model Generation (2022.coling-1)

Copied to clipboard

Challenge: Large pretrained language models can generate powerful text but cannot be controlled at a sub-sentential level.
Approach: They propose to make such fine-grained control possible in pretrained LMs by generating text directly from a semantic representation, Abstract Meaning Representation (BART), which is augmented at the node level with syntactic control tags.
Outcome: The proposed method can generate text from a semantic representation, which is augmented at the node level with syntactic control tags.

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