276 citations · 2k across the 138 of their papers we have counts for
102 papers · 1 filter
Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Liangming Pan, Michael Saxon, Wenda Xu +3
Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behavior…
Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou +9
We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data. Our…
Multilingual Conceptual Coverage in Text-to-Image Models
Michael Saxon, William Yang Wang
We propose "Conceptual Coverage Across Languages" (CoCo-CroLa), a technique for benchmarking the degree to which any generative text-to-image system provides multilingual parity to…
Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Xingyu Fu, Sheng Zhang, Gukyeong Kwon +10
The open-ended Visual Question Answering (VQA) task requires AI models to jointly reason over visual and natural language inputs using world knowledge. Recently, pre-trained Langua…
Fact-Checking Complex Claims with Program-Guided Reasoning
Liangming Pan, Xiaobao Wu, Xinyuan Lu +4
Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning. In this paper, we present Program-Guided Fact-Check…
Multimodal Procedural Planning via Dual Text-Image Prompting
Yujie Lu, Pan Lu, Zhiyu Chen +3
Embodied agents have achieved prominent performance in following human instructions to complete tasks. However, the potential of providing instructions informed by texts and images…
DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
Xianjun Yang, Wei Cheng, Yue Wu +3
Large language models (LLMs) have notably enhanced the fluency and diversity of machine-generated text. However, this progress also presents a significant challenge in detecting th…
ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers
Kexun Zhang, Danqing Wang, Jingtao Xia +2
Large language models (LLMs) excel at implementing code from functionality descriptions but struggle with algorithmic problems that require not only implementation but also identif…
Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning
Liangming Pan, Alon Albalak, Xinyi Wang +1
Large Language Models (LLMs) have shown human-like reasoning abilities but still struggle with complex logical problems. This paper introduces a novel framework, Logic-LM, which in…
Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation
Wanrong Zhu, Xinyi Wang, Yujie Lu +4
The field of text-to-image (T2I) generation has garnered significant attention both within the research community and among everyday users. Despite the advancements of T2I models,…
Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings
Daniel Rose, Vaishnavi Himakunthala, Andy Ouyang +7
Recent advances in large language models elicit reasoning in a chain-of-thought that allows models to decompose problems in a human-like fashion. Though this paradigm improves mult…
STREET: A Multi-Task Structured Reasoning and Explanation Benchmark
Danilo Ribeiro, Shen Wang, Xiaofei Ma +10
We introduce STREET, a unified multi-task and multi-domain natural language reasoning and explanation benchmark. Unlike most existing question-answering (QA) datasets, we expect mo…
Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness
Shuaichen Chang, Jun Wang, Mingwen Dong +13
Neural text-to-SQL models have achieved remarkable performance in translating natural language questions into SQL queries. However, recent studies reveal that text-to-SQL models ar…
SWING: Balancing Coverage and Faithfulness for Dialogue Summarization
Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma +5
Missing information is a common issue of dialogue summarization where some information in the reference summaries is not covered in the generated summaries. To address this issue,…
Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
Xinyi Wang, Wanrong Zhu, Michael Saxon +2
In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context le…
Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations
Jifan Chen, Yuhao Zhang, Lan Liu +5
There has been great progress in unifying various table-to-text tasks using a single encoder-decoder model trained via multi-task learning (Xie et al., 2022). However, existing met…
CausalDialogue: Modeling Utterance-level Causality in Conversations
Yi-Lin Tuan, Alon Albalak, Wenda Xu +4
Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and…
Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks
Kaiser Sun, Peng Qi, Yuhao Zhang +3
Generative models have been widely applied to solve extractive tasks, where parts of the input is extracted to form the desired output, and achieved significant success. For exampl…
Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI
Alex Mei, Sharon Levy, William Yang Wang
Users' physical safety is an increasing concern as the market for intelligent systems continues to grow, where unconstrained systems may recommend users dangerous actions that can…
SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes
Wenda Xu, Xian Qian, Mingxuan Wang +2
Is it possible to train a general metric for evaluating text generation quality without human annotated ratings? Existing learned metrics either perform unsatisfactorily across tex…
WikiWhy: Answering and Explaining Cause-and-Effect Questions
Matthew Ho, Aditya Sharma, Justin Chang +4
As large language models (LLMs) grow larger and more sophisticated, assessing their "reasoning" capabilities in natural language grows more challenging. Recent question answering (…
Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Wenda Xu, Yilin Tuan, Yujie Lu +3
Is it possible to build a general and automatic natural language generation (NLG) evaluation metric? Existing learned metrics either perform unsatisfactorily or are restricted to t…
Bridging the Training-Inference Gap for Dense Phrase Retrieval
Gyuwan Kim, Jinhyuk Lee, Barlas Oguz +4
Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these proced…
An Exploration of Data Efficiency in Intra-Dataset Task Transfer for Dialog Understanding
Josiah Ross, Luke Yoffe, Alon Albalak +1
Transfer learning is an exciting area of Natural Language Processing that has the potential to both improve model performance and increase data efficiency. This study explores the…