165 citations · 469 across the 30 of their papers we have counts for
16 papers · 1 filter
CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions
Mourad Heddaya, Kyle MacMillan, Anup Malani +2
This paper introduces CaseSumm, a novel dataset for long-context summarization in the legal domain that addresses the need for longer and more complex datasets for summarization ev…
FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering
Siqiao Xue, Xiaojing Li, Fan Zhou +3
In this paper, we introduce FAMMA, an open-source benchmark for \underline{f}in\underline{a}ncial \underline{m}ultilingual \underline{m}ultimodal question \underline{a}nswering (QA…
MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models
Peng Ding, Jiading Fang, Peng Li +6
Large language models such as ChatGPT and GPT-4 have recently achieved astonishing performance on a variety of natural language processing tasks. In this paper, we propose MANGO, a…
WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine
Siqiao Xue, Fan Zhou, Yi Xu +10
We present WeaverBird, an intelligent dialogue system designed specifically for the finance domain. Our system harnesses a large language model of GPT architecture that has been tu…
Autoregressive Modeling with Lookahead Attention
Li Du, Hongyuan Mei, Jason Eisner
To predict the next token, autoregressive models ordinarily examine the past. Could they also benefit from also examining hypothetical futures? We consider a novel Transformer-base…
Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning
Xiaoming Shi, Siqiao Xue, Kangrui Wang +5
Large language models have shown astonishing performance on a wide range of reasoning tasks. In this paper, we investigate whether they could reason about real-world events and hel…
Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions
Chen Feng Tsai, Xiaochen Zhou, Sierra S. Liu +3
Large language models (LLMs) such as ChatGPT and GPT-4 have recently demonstrated their remarkable abilities of communicating with human users. In this technical report, we take an…
Explicit Planning Helps Language Models in Logical Reasoning
Hongyu Zhao, Kangrui Wang, Mo Yu +1
Language models have been shown to perform remarkably well on a wide range of natural language processing tasks. In this paper, we propose LEAP, a novel system that uses language m…
Robustness of Learning from Task Instructions
Jiasheng Gu, Hongyu Zhao, Hanzi Xu +3
Traditional supervised learning mostly works on individual tasks and requires training on a large set of task-specific examples. This paradigm seriously hinders the development of…
Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning
Shuo Xie, Jiahao Qiu, Ankita Pasad +3
While transferring a pretrained language model, common approaches conventionally attach their task-specific classifiers to the top layer and adapt all the pretrained layers. We inv…
Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters
Hongyu Zhao, Hao Tan, Hongyuan Mei
Adapter-tuning is a paradigm that transfers a pretrained language model to downstream tasks by adding and tuning a small number of new parameters. Previously proposed adapter archi…
On the Idiosyncrasies of the Mandarin Chinese Classifier System
Shijia Liu, Hongyuan Mei, Adina Williams +1
While idiosyncrasies of the Chinese classifier system have been a richly studied topic among linguists (Adams and Conklin, 1973; Erbaugh, 1986; Lakoff, 1986), not much work has bee…
Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction
Hongyuan Mei, Sheng Zhang, Kevin Duh +1
Cross-lingual information extraction (CLIE) is an important and challenging task, especially in low resource scenarios. To tackle this challenge, we propose a training method, call…
Coherent Dialogue with Attention-based Language Models
Hongyuan Mei, Mohit Bansal, Matthew R. Walter
We model coherent conversation continuation via RNN-based dialogue models equipped with a dynamic attention mechanism. Our attention-RNN language model dynamically increases the sc…
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment
Hongyuan Mei, Mohit Bansal, Matthew R. Walter
We propose an end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i.e., the joint task of content selection and surface realization. Our m…
Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
Hongyuan Mei, Mohit Bansal, Matthew R. Walter
We propose a neural sequence-to-sequence model for direction following, a task that is essential to realizing effective autonomous agents. Our alignment-based encoder-decoder model…