Papers by Bing Xiang

AnRe: Analogical Replay for Temporal Knowledge Graph Forecasting (2025.acl-long)

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.

Copied to clipboard

Guo Tang, Zheng Chu, Wenxiang Zheng, Junjia Xiang, Yizhuo Li, Weihao Zhang, Ming Liu, Bing Qin

DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)

Challenge:	Temporal Knowledge Graphs (TKGs) are vital for event prediction, yet current methods face limitations.
Approach:	They propose a training-free Analogical Replay reasoning framework that uses LLMs to extract historical contexts and generate analogical reasoning examples as contextual inputs.
Outcome:	The proposed model outperforms existing training-free methods on four benchmarks.

Copied to clipboard

Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xin Liu, Zhengyang Wang, Xianfeng Tang, Shiyang Li, Xiang He, Ruijie Wang, Bing Yin, Xiao Gu, Lei Clifton, David A. Clifton

Topic Modeling with Wasserstein Autoencoders (P19-1)

Challenge:	commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools .
Approach:	They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression .
Outcome:	The proposed approach outperforms human experts in medical examinations on diverse datasets.

Copied to clipboard

Feng Nan, Ran Ding, Ramesh Nallapati, Bing Xiang

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)

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.

Copied to clipboard

Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang

Programming Languages in NLP

Challenge:	Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data.
Approach:	They propose a framework that imposes strong typing constraints and incorporates key relationships from schema.
Outcome:	The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider.

Efficient Shapley Values Estimation by Amortization for Text Classification (2023.acl-long)

Copied to clipboard

Chenghao Yang, Fan Yin, He He, Kai-Wei Chang, Xiaofei Ma, Bing Xiang

Information Retrieval

Challenge:	Shapley Values are often estimated with a small number of stochastic model evaluations, but this can only be mitigated by aggregating thousands of model evaluation.
Approach:	They propose to combine a model with thousands of model evaluations to estimate Shapley Values without additional model evaluation.
Outcome:	The proposed model estimates Shapley Values accurately with up to 60 times speedup compared to traditional methods and does not suffer from stability issues as inference is deterministic.

Learning Dialogue Representations from Consecutive Utterances (2022.naacl-main)

Copied to clipboard

Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew Arnold, Bing Xiang

Contrastive Document Representation Learning with Graph Attention Networks (2021.findings-emnlp)

Challenge:	Dialogue Sentence Embedding (DSE) is a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue-oriented tasks.
Approach:	They propose a self-supervised contrastive learning method that learns dialogue representations suitable for a wide range of dialogue tasks.
Outcome:	The proposed method outperforms baselines on five dialogue tasks on a few-shot and zero-shot datasets.

Copied to clipboard

Peng Xu, Xinchi Chen, Xiaofei Ma, Zhiheng Huang, Bing Xiang

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction (2021.acl-long)

Challenge:	Existing methods for document representation learning are significantly affected by the scarcity of document-level data.
Approach:	They propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings.
Outcome:	Empirically, the proposed approach is effective in document classification and document retrieval tasks.

Copied to clipboard

Yifan Gao, Henghui Zhu, Patrick Ng, Cicero Nogueira dos Santos, Zhiguo Wang, Feng Nan, Dejiao Zhang, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Natural Language Interfaces

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.

Retrieval, Re-ranking and Multi-task Learning for Knowledge-Base Question Answering (2021.eacl-main)

Copied to clipboard

Zhiguo Wang, Patrick Ng, Ramesh Nallapati, Bing Xiang

From Implicit Graph Encoding to Explicit Evidence: A Training-Free LLM Framework for Temporal Knowledge Graph Reasoning (2026.findings-acl)

Challenge:	Existing work on question answering over knowledge bases limited the search space to a subset of KBs . a retrieval-and-rerank framework is used to access KB and rerank retrieved candidates with more powerful neural networks.
Approach:	They propose to share a BERT encoder across all three sub-tasks and define task-specific layers on top of the shared layer.
Outcome:	The proposed method improves accuracy and accuracy on the SimpleQuestions dataset and the FreebaseQA dataset.

Copied to clipboard

Guo Tang, Ke Cheng, Huiming Fan, Heng Chang, Wenxiang Zheng, Xianhao Ou, Junjia Xiang, Ming Liu, Yujun Zhou, Li Lanyu, Bing Qin

Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning (2025.acl-long)

Challenge:	Existing Large Language Models (LLMs) struggle with implicit modality alignment and suboptimal graph linearization.
Approach:	They propose a training-free, test-time adaptive framework that reframes TKG prediction as explicit evidence-driven reasoning.
Outcome:	ExE-LLM outperforms fully trained graph neural networks on four benchmarks . it achieves SOTA performance in inductive settings, significantly outperforming fully trained neural networks .

Copied to clipboard

Yexing Du, Youcheng Pan, Ziyang Ma, Bo Yang, Yifan Yang, Keqi Deng, Xie Chen, Yang Xiang, Ming Liu, Bing Qin

Entity-level Factual Consistency of Abstractive Text Summarization (2021.eacl-main)

Challenge:	Existing studies on English-centric translation tasks have focused on multimodal large language models, but the exploration of many-to-many translation is limited by the scarcity of parallel data.
Approach:	They propose a three-stage curriculum learning strategy that leverages the machine translation capabilities of large language models and adapts them to S2TT tasks.
Outcome:	The proposed strategy achieves state-of-the-art average performance in 1514 language pairs, requiring fewer than 10 hours of speech data per language to achieve competitive results.

Copied to clipboard

Feng Nan, Ramesh Nallapati, Zhiguo Wang, Cicero Nogueira dos Santos, Henghui Zhu, Dejiao Zhang, Kathleen McKeown, Bing Xiang

CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention (2025.acl-long)

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.

Copied to clipboard

Zekai Ye, Qiming Li, Xiaocheng Feng, Libo Qin, Yichong Huang, Baohang Li, Kui Jiang, Yang Xiang, Zhirui Zhang, Yunfei Lu, Duyu Tang, Dandan Tu, Bing Qin

Reasoning

Challenge:	Large Vision-Language Models (LVLMs) have impressive multimodal abilities but remain prone to multilingual object hallucination.
Approach:	They propose a cross-lingual attention intervention method to mitigate multilingual object hallucination in LVLMs by aligning attention patterns.
Outcome:	The proposed method improves 13.56% (up to 30%) on the POPE and 21.75% on the hallucination subsets across languages.

Hierarchical Pointer Net Parsing (D19-1)

Copied to clipboard

Linlin Liu, Xiang Lin, Shafiq Joty, Simeng Han, Lidong Bing

Challenge:	Existing approaches to parsing are greedy transition-based and globally optimized . however, the decision-making process is based on local information, causing error propagation to subsequent steps.
Approach:	They propose hierarchical pointer network parsers and apply them to dependency and sentence-level discourse parsing tasks.
Outcome:	The proposed method outperforms existing methods and sets new state-of-the-art methods on benchmark datasets.

Token Alignment via Character Matching for Subword Completion (2024.findings-acl)

Copied to clipboard

Ben Athiwaratkun, Shiqi Wang, Mingyue Shang, Yuchen Tian, Zijian Wang, Sujan Kumar Gonugondla, Sanjay Krishna Gouda, Robert Kwiatkowski, Ramesh Nallapati, Parminder Bhatia, Bing Xiang

Low-Resource NLP

Challenge:	Generative models struggle with prompts corresponding to partial tokens due to tokenization, where partial token is out-of-distribution during inference.
Approach:	They propose a method to alleviate tokenization artifact on text completion by backtracking to the last complete tokens and aligning subsequent generations to match with the prompt.
Outcome:	The proposed method shows that it improves on partial token scenarios with only a minor time increase.

Benchmarking Diverse-Modal Entity Linking with Generative Models (2023.findings-acl)

Copied to clipboard

Sijia Wang, Alexander Hanbo Li, Henghui Zhu, Sheng Zhang, Pramuditha Perera, Chung-Wei Hang, Jie Ma, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng

Margin-aware Unsupervised Domain Adaptation for Cross-lingual Text Labeling (2020.findings-emnlp)

Challenge:	Existing models for diverse-mode entity linking (EL) work well on per modality configurations, but it is more challenging to design a unified model for diverse modality.
Approach:	They propose a generative diverse-modal model that integrates text, image and table . they propose combining a multimodal encoder-decoder paradigm with a fine-tuning GDMM .
Outcome:	The proposed model outperforms state-of-the-art models by 8.51 F1 on average for diverse-modal EL.

Copied to clipboard

Dejiao Zhang, Ramesh Nallapati, Henghui Zhu, Feng Nan, Cicero Nogueira dos Santos, Kathleen McKeown, Bing Xiang

Low-Resource NLP

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.

Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering (2020.acl-main)

Copied to clipboard

Alexander Fabbri, Patrick Ng, Zhiguo Wang, Ramesh Nallapati, Bing Xiang

Low-Resource NLP

Challenge:	Question Answering (QA) is a field of increasing demand due to the availability of information online.
Approach:	They propose an unsupervised approach to training QA models with generated pseudo-training data by applying a simple template on a related sentence rather than the original context sentence.
Outcome:	The proposed approach improves the performance of a QA model on generated pseudo-training data.

RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering (2023.findings-acl)

Copied to clipboard

Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang, Dan Roth

Responsible & Trustworthy NLP

Challenge:	Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models’ generalizability across diverse domains.
Approach:	They propose a benchmark to evaluate ODQA's domain robustness using Wikipedia corpus . they annotate QA pairs in retrieval datasets with rigorous quality control .
Outcome:	The proposed benchmark improves model performance on annotated QA pairs in retrieval datasets with rigorous quality control.

MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus (2026.findings-acl)

Copied to clipboard

Yexing Du, Kaiyuan Liu, Bihe Zhang, Youcheng Pan, Bo Yang, Liangyu Huo, Xiyuan Zhang, Jian Xie, Daojing He, Yang Xiang, Ming Liu, Bing Qin

Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning (2023.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced Chinese Classical Studies (CCS) but the audio dimension of CCS remains underexplored due to a lack of high-quality, domain-specific audio corpora.
Approach:	They propose a 119-hour audio corpus comprising 22,000 audio samples to bridge this gap . it encompasses a diverse range of literary genres across six tasks .
Outcome:	The proposed corpus encompasses a diverse range of literary genres across six tasks: Automatic Speech Recognition (ASR), Speech-to-Text Translation (S2TT), Speech Emotion Captioning (SEC), Spoken Question Answering ( SQA), Speech Understanding (SU), and Speech Reasoning (SR).

Copied to clipboard

Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou, Jie Ma, Patrick Ng, Zhiguo Wang, Bonan Min, William Yang Wang, Kathleen McKeown, Vittorio Castelli, Dan Roth, Bing Xiang

Exploring Continual Learning for Code Generation Models (2023.acl-short)

Challenge:	Existing methods for data-to-text generation focus on specific types of structured data.
Approach:	They propose a method that provides a unified representation that can handle various forms of structured data such as tables, knowledge graph triples, and meaning representations.
Outcome:	The proposed method improves zero-shot and few-shot scenarios and can adapt to new structured data.

Copied to clipboard

Prateek Yadav, Qing Sun, Hantian Ding, Xiaopeng Li, Dejiao Zhang, Ming Tan, Parminder Bhatia, Xiaofei Ma, Ramesh Nallapati, Murali Krishna Ramanathan, Mohit Bansal, Bing Xiang

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering (2021.acl-long)

Challenge:	Large-scale code generation models such as Copilot and CodeT5 are expensive to train and re-train.
Approach:	They propose a benchmark for Continual Learning (CL) that covers a wide range of tasks with different input and output programming languages.
Outcome:	The proposed method improves on Prompt Pooling with Teacher Forcing, which suffers catastrophic forgetting due to stark distribution shifts in coding tasks.

Copied to clipboard

Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang

Coherence-Aware Neural Topic Modeling (D18-1)

Challenge:	Existing generative models for open-domain question answering focus on generating direct answers from unstructured textual information, but a large amount of knowledge is stored in structured databases, and need to be accessed using query languages such as SQL.
Approach:	They propose a hybrid framework that takes both textual and tabular evidences as input and generates either direct answers or SQL queries depending on which form could better answer the question.
Outcome:	The proposed framework outperforms baseline models on OpenSQuAD datasets and can generate SQL queries on the associated databases to obtain the final answers.

Copied to clipboard

Ran Ding, Ramesh Nallapati, Bing Xiang

Information Extraction & Text Mining

Challenge:	Topic models are evaluated for their ability to describe documents well (i.e. low perplexity) topic coherence is not optimized for and is only evaluated after training.
Approach:	They propose to incorporate a topic coherence objective into the training process by incorporating a coherency objective into a model.
Outcome:	The proposed model exhibits similar level of perplexity as baseline models but significantly higher topic coherence.

Supporting Clustering with Contrastive Learning (2021.naacl-main)

Copied to clipboard

Dejiao Zhang, Feng Nan, Xiaokai Wei, Shang-Wen Li, Henghui Zhu, Kathleen McKeown, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Improving Text-to-SQL Semantic Parsing with Fine-grained Query Understanding (2022.emnlp-industry)

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.

Copied to clipboard

Jun Wang, Patrick Ng, Alexander Hanbo Li, Jiarong Jiang, Zhiguo Wang, Bing Xiang, Ramesh Nallapati, Sudipta Sengupta

Programming Languages in NLP

Challenge:	Recent research on Text-to-SQL semantic parsing relies on parser or heuristic based approach to understand natural language query.
Approach:	They propose a general-purpose, modular neural semantic parsing framework that is based on token-level fine-grained query understanding.
Outcome:	The proposed framework outperforms the state-of-the-art model by 2.7% on a WikiTableQuestions test set.

DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization (2022.acl-short)

Copied to clipboard

Zheng Li, Zijian Wang, Ming Tan, Ramesh Nallapati, Parminder Bhatia, Andrew Arnold, Bing Xiang, Dan Roth

Augmented Natural Language for Generative Sequence Labeling (2020.emnlp-main)

Challenge:	Empirical analyses show that pre-trained sequence-to-sequence models can achieve a 16.5x model footprint compression ratio with little performance drop relative to full-precision counterparts.
Approach:	They propose to distill and quantize pre-trained sequence-to-sequence models to reduce memory and latency requirements.
Outcome:	Empirical results show that the proposed model achieves 16.5x model footprint compression ratio with little performance drop relative to full-precision counterparts on multiple summarization and QA datasets.

Copied to clipboard

Ben Athiwaratkun, Cicero Nogueira dos Santos, Jason Krone, Bing Xiang

Information Retrieval

Challenge:	generative framework for joint sequence labeling and sentence-level classification is general purpose, performing well on few-shot learning, low resource, and high resource tasks.
Approach:	They propose a generative framework for joint sequence labeling and sentence-level classification . their framework incorporates label semantics and shares knowledge across tasks .
Outcome:	The proposed model performs on few-shot learning, slot labeling, and intent classification benchmarks.

Improving Factual Consistency of Abstractive Summarization via Question Answering (2021.acl-long)

Copied to clipboard

Feng Nan, Cicero Nogueira dos Santos, Henghui Zhu, Patrick Ng, Kathleen McKeown, Ramesh Nallapati, Dejiao Zhang, Zhiguo Wang, Andrew O. Arnold, Bing Xiang

Summarization

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.

Beyond [CLS] through Ranking by Generation (2020.emnlp-main)

Copied to clipboard

Cicero Nogueira dos Santos, Xiaofei Ma, Ramesh Nallapati, Zhiheng Huang, Bing Xiang

Information Retrieval

Challenge:	Recent work on generative ranking models for Information Retrieval has focused on discriminative methods that learn a similarity function to compare questions and candidates answers.
Approach:	They propose to use a language model to train a ranking function that model the semantic similarity of documents and queries instead of discriminative ranking functions.
Outcome:	The proposed approaches are as effective as state-of-the-art discriminative models for the answer selection task and show unlikelihood losses are reduced for IR.

Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering (P18-2)

Copied to clipboard

Rui Zhang, Cícero Nogueira dos Santos, Michihiro Yasunaga, Bing Xiang, Dragomir Radev

Information Extraction & Text Mining

Challenge:	Existing methods for identifying and clustering mentions in text are complex and require heuristics to solve.
Approach:	They propose to use a biaffine attention model to get antecedent scores for each possible mention and optimize mention detection and mention clustering accuracy given the mention cluster labels.
Outcome:	The proposed model achieves the state-of-the-art performance on the CoNLL-2012 shared task English test set.

Lightweight reranking for language model generations (2024.acl-long)

Copied to clipboard

Siddhartha Jain, Xiaofei Ma, Anoop Deoras, Bing Xiang

ContraCLM: Contrastive Learning For Causal Language Model (2023.acl-long)

Challenge:	Large Language Models (LLMs) can exhibit considerable variation in quality of sampled outputs.
Approach:	They propose a method for reranking LLM generations using pairwise statistics . they show strong improvements for selecting the best k generations for code generation tasks .
Outcome:	The proposed approach improves selection and generation quality for code generation tasks and autoformalization, summarization, and translation tasks.

Copied to clipboard

Nihal Jain, Dejiao Zhang, Wasi Uddin Ahmad, Zijian Wang, Feng Nan, Xiaopeng Li, Ming Tan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Bing Xiang

Domain Adaptation with BERT-based Domain Classification and Data Selection (D19-61)

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.

Copied to clipboard

Xiaofei Ma, Peng Xu, Zhiguo Wang, Ramesh Nallapati, Bing Xiang

CoCoMIC: Code Completion by Jointly Modeling In-file and Cross-file Context (2024.lrec-main)

Challenge:	Modern deep neural models with millions of parameters can easily adapt to a new learning task and dataset when enough supervision is given.
Approach:	They propose a domain adaptation framework based on curriculum learning and domain-discriminative data selection.
Outcome:	The proposed framework outperforms discrepancy-based methods on transfer tasks while consuming only fraction of training budget.

Copied to clipboard

Yangruibo Ding, Zijian Wang, Wasi U. Ahmad, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, Bing Xiang

Pairwise Supervised Contrastive Learning of Sentence Representations (2021.emnlp-main)

Challenge:	Pre-trained language models (LMs) for code have shown promising performance in code completion tasks but ignore the rich semantics in other files within the same project.
Approach:	They propose a framework that jointly learns the in-file and cross-file context on top of code LMs and a static-analysis-based tool that locates and retrieves the most relevant project-level cross- file context for code completion.
Outcome:	The proposed framework improves existing code LMs with a 33.94% relative increase in exact match and 28.69% in identifier matching when the cross-file context is provided.

Copied to clipboard

Dejiao Zhang, Shang-Wen Li, Wei Xiao, Henghui Zhu, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Generative Context Pair Selection for Multi-hop Question Answering (2021.emnlp-main)

Challenge:	Recent efforts to improve sentence representation learning have a common weakness . siamese or triplet loss only learns from individual sentence pairs or tripletes .
Approach:	They propose a discrimination-based approach to bridge entailment and contradiction understanding with categorical concept encoding.
Outcome:	The proposed method outperforms the state-of-the-art method on downstream tasks . it improves 10%–13% on clustering tasks and 5%–6% on STS tasks compared with the previous method .

Copied to clipboard

Dheeru Dua, Cicero Nogueira dos Santos, Patrick Ng, Ben Athiwaratkun, Bing Xiang, Matt Gardner, Sameer Singh

Reasoning

Challenge:	Recent studies have shown that discriminative training results in models that exploit these underlying biases to achieve a better held-out performance, without learning the right way to reason.
Approach:	They propose a generative context selection model for multi-hop QA that reasons about how the given question could have been generated given a context pair and not just independent contexts.
Outcome:	The proposed model outperforms the state-of-the-art model on hotpotQA while being comparable to the state of the art answering performance on adversarial held-out set.

SCOTT: Self-Consistent Chain-of-Thought Distillation (2023.acl-long)

Copied to clipboard

Peifeng Wang, Zhengyang Wang, Zheng Li, Yifan Gao, Bing Yin, Xiang Ren

Improve Transformer Models with Better Relative Position Embeddings (2020.findings-emnlp)

Challenge:	Large language models (LMs) generate free-text rationales for their predictions via chain-of-thought prompting, but there is little guarantee that the generated rationale is consistent with LM’s predictions or faithfully justify the decisions.
Approach:	They propose a faithful knowledge distillation method to learn a small, self-consistent CoT model from a larger teacher model by contrastive decoding.
Outcome:	The proposed method yields comparable performance but is less faithful than baselines.

Copied to clipboard

Zhiheng Huang, Davis Liang, Peng Xu, Bing Xiang

Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering (D19-1)

Challenge:	Existing methods for generating position embeddings are not fully utilized in NLP tasks.
Approach:	They propose to generalize the absolute position embedding to a generalized relative position embedded method . they also propose to use the relative embeddable method to improve the accuracy of large models .
Outcome:	The proposed method improves accuracy on the SQuAD1.1 dataset compared to previous methods . it can be easily adopted as a drop-in replacement for improving accuracy of large models .

Copied to clipboard

Zhiguo Wang, Patrick Ng, Xiaofei Ma, Ramesh Nallapati, Bing Xiang

Natural Language Interfaces

Challenge:	Existing studies have shown that BERT models can find answers from multiple passages . however, the results of these studies are still unaddressed.
Approach:	They propose a multi-passage BERT model to globally normalize answer scores across all passages of the same question.
Outcome:	The proposed model outperforms state-of-the-art models on four benchmarks.

Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge (2023.findings-acl)

Copied to clipboard

Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henghui Zhu, Yuhao Zhang, Alexander Hanbo Li, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang