Papers by Dan Su

14 papers
Task-Oriented Dialogue as Dataflow Synthesis (2020.tacl-1)

Copied to clipboard

Challenge: Existing approaches to task-oriented dialogue represent dialogue state as a dataflow graph . microsoft's SMCalFlow dataset features complex dialogues about events, weather, places, and people .
Approach: They propose a dataflow graph-based dialogue agent that maps each user utterance to a program that extends this graph.
Outcome: The proposed framework improves representability and predictability in natural dialogues . it uses dataflow graphs and metacomputation to map user intents to a program .
Context Generation Improves Open Domain Question Answering (2023.findings-eacl)

Copied to clipboard

Challenge: Existing closed-book question answering methods do not fully exploit the parameterized knowledge.
Approach: They propose a closed-book QA framework which uses a coarse-to-fine approach to extract the relevant knowledge and answer a question.
Outcome: The proposed method outperforms open-book QA methods on three QA benchmarks.
Multi-hop Question Generation with Graph Convolutional Network (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on text-based QG focus on generating SQuAD-style questions.
Approach: They propose a multi-hop question generation model that does context encoding in multiple hops with Graph Convolutional Network and encoder fusion via an Encoder Reasoning Gate.
Outcome: Empirical results show that the proposed model generates fluent questions with high completeness and outperforms baselines on automatic evaluation metrics.
Generalizing Question Answering System with Pre-trained Language Model Fine-tuning (D19-58)

Copied to clipboard

Challenge: Existing methods focus on improving in-domain performance, leaving open the question of how they can generalize to out-of-domain and unseen RC tasks.
Approach: They propose a multi-task learning framework that learns the shared representation across different tasks and builds on a large pre-trained language model and fine-tuned on multiple RC datasets.
Outcome: The proposed framework improves the BERT-Large baseline by 8.39 and 7.22 respectively.
Read before Generate! Faithful Long Form Question Answering with Machine Reading (2022.findings-acl)

Copied to clipboard

Challenge: Long-form question answering (LFQA) generates a paragraph-length answer for a given question.
Approach: They propose a framework that jointly models answer generation and machine reading.
Outcome: The proposed model generates a more factually accurate answer from millions of documents retrieved from a large dataset.
Suggest-Verify-Revise: A Three-Stage Document-Level Event Causality Identification with Narrative Consistency (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for document-level Event Causality Identification rely on local semantic similarity for independent event-pair discrimination . Existing approaches ignore the influence of the overall narrative backbone in the propagation of causal dependencies and the role differentiation of events within multi-cause/multi-effect structures.
Approach: They propose a suggest-verify-revise approach for document-level Event Causality Identification with narrative consistency (SVRECI) they integrate heuristic causal suggestions generated by an LLM with structural suggestions derived from hypergraph modeling .
Outcome: The proposed approach outperforms existing methods on event-storylines and Causal-TimeBank datasets.
NusaCrowd: Open Source Initiative for Indonesian NLP Resources (2023.findings-acl)

Copied to clipboard

Challenge: Existing NLP research in Indonesian languages has been held back by factors such as language diversity, orthographic variation, resource limitation and other societal challenges.
Approach: They present a collaborative initiative to collect and unify existing resources for Indonesian languages and open access to previously non-public resources.
Outcome: The results show that the datasets are highly reliable and can be used to generate the first zero-shot benchmarks for natural language understanding and generation in Indonesian and the local languages of Indonesia.
Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer (2024.acl-long)

Copied to clipboard

Challenge: Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity.
Approach: They propose a hierarchical transformer that quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a transformer architecture.
Outcome: The proposed model outperforms existing speech language models in word error rate, speech quality, and speaker similarity.
GSM-Noise: Exploring and Enhancing Large Language Models’ Reasoning under Noisy Inputs (2026.findings-acl)

Copied to clipboard

Challenge: Large language models struggle when dealing with complex, ill-formed, or noisy inputs . open-source models are less robust, while closed-source ones are more robust .
Approach: They propose to use GSM-Noise to refine inputs before engaging in in-depth analysis to improve LLM robustness under noisy conditions.
Outcome: The proposed model can achieve consistent performance gains under noisy conditions with prompt engineering, supervised finetuning, and reinforcement learning.
Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance (2021.findings-acl)

Copied to clipboard

Challenge: Query focused summarization models aim to generate summaries from source documents that can answer the given query.
Approach: They propose a QFS-BART model that incorporates the explicit answer relevance of the source documents given the query via a question answering model.
Outcome: Empirical results show that the proposed model achieves the new state-of-the-art performance.
Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training (2023.eacl-main)

Copied to clipboard

Challenge: Large-scale vision-language pre-trained (VLP) models generate unfaithful or nonsensical texts given the source input, which is called hallucination.
Approach: They propose a VLP loss-based model to mitigate object hallucination by decoupling VLP objectives and a token-level image-text alignment.
Outcome: The proposed model reduces object hallucination by 17.4% on two benchmarks.
MM-LLMs: Recent Advances in MultiModal Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: MultiModal Large Language Models (MM-LLMs) have undergone significant advances in the past year . traditional MM models incur substantial computational costs, especially when trained from scratch .
Approach: They propose a taxonomy encompassing 126 MM-LLMs and summarize key training recipes to enhance their potency.
Outcome: The proposed models preserve the reasoning and decision-making capabilities of LLMs and empower diverse range of MM tasks.
Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset (2025.acl-long)

Copied to clipboard

Challenge: Recent Common Crawl datasets remove 90% of data, limiting their suitability for long token horizon training.
Approach: They propose to combine classifier ensembling, synthetic data rephrasing and heuristic filters to achieve better trade-offs between accuracy and data quantity.
Outcome: The proposed model-based filtering improves MMLU by 5.6 over DCLM for 15T tokens . the full 6.3T token dataset matches DCLM on MMLO, but contains four times more unique real tokens than DCLM .
A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners (2024.emnlp-main)

Copied to clipboard

Challenge: a new hypothesis-testing framework is developed to assess whether large language models possess genuine reasoning abilities or primarily depend on token bias.
Approach: They propose a framework to assess whether large language models have genuine reasoning abilities or primarily depend on token bias.
Outcome: The proposed framework outlines a list of hypotheses where token biases are readily identifiable . the results suggest that most LLMs still struggle with logical reasoning .

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