Search Results for author: He He

Found 67 papers, 38 papers with code

Robustness and Adversarial Examples in Natural Language Processing

no code implementations EMNLP (ACL) 2021 Kai-Wei Chang, He He, Robin Jia, Sameer Singh

In particular, we will review recent studies on analyzing the weakness of NLP systems when facing adversarial inputs and data with a distribution shift.

Iterative Reasoning Preference Optimization

no code implementations30 Apr 2024 Richard Yuanzhe Pang, Weizhe Yuan, Kyunghyun Cho, He He, Sainbayar Sukhbaatar, Jason Weston

Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024).

GSM8K Math

Parallel Structures in Pre-training Data Yield In-Context Learning

no code implementations19 Feb 2024 Yanda Chen, Chen Zhao, Zhou Yu, Kathleen McKeown, He He

Pre-trained language models (LMs) are capable of in-context learning (ICL): they can adapt to a task with only a few examples given in the prompt without any parameter update.

In-Context Learning

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning

1 code implementation25 Jan 2024 Yanda Chen, Chandan Singh, Xiaodong Liu, Simiao Zuo, Bin Yu, He He, Jianfeng Gao

We propose explanation-consistency finetuning (EC-finetuning), a method that adapts LLMs to generate more consistent natural-language explanations on related examples.

Question Answering

Pragmatic Radiology Report Generation

1 code implementation28 Nov 2023 Dang Nguyen, Chacha Chen, He He, Chenhao Tan

When pneumonia is not found on a chest X-ray, should the report describe this negative observation or omit it?

Show Your Work with Confidence: Confidence Bands for Tuning Curves

1 code implementation16 Nov 2023 Nicholas Lourie, Kyunghyun Cho, He He

We present the first method to construct valid confidence bands for tuning curves.

Personas as a Way to Model Truthfulness in Language Models

no code implementations27 Oct 2023 Nitish Joshi, Javier Rando, Abulhair Saparov, Najoung Kim, He He

This allows the model to separate truth from falsehoods and controls the truthfulness of its generation.

Does Writing with Language Models Reduce Content Diversity?

1 code implementation11 Sep 2023 Vishakh Padmakumar, He He

We develop a set of diversity metrics and find that writing with InstructGPT (but not the GPT3) results in a statistically significant reduction in diversity.

Leveraging Implicit Feedback from Deployment Data in Dialogue

no code implementations26 Jul 2023 Richard Yuanzhe Pang, Stephen Roller, Kyunghyun Cho, He He, Jason Weston

We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations.

Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations

no code implementations17 Jul 2023 Yanda Chen, Ruiqi Zhong, Narutatsu Ri, Chen Zhao, He He, Jacob Steinhardt, Zhou Yu, Kathleen McKeown

To answer these questions, we propose to evaluate $\textbf{counterfactual simulatability}$ of natural language explanations: whether an explanation can enable humans to precisely infer the model's outputs on diverse counterfactuals of the explained input.


Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples

1 code implementation NeurIPS 2023 Abulhair Saparov, Richard Yuanzhe Pang, Vishakh Padmakumar, Nitish Joshi, Seyed Mehran Kazemi, Najoung Kim, He He

Given the intractably large size of the space of proofs, any model that is capable of general deductive reasoning must generalize to proofs of greater complexity.

Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations

1 code implementation22 May 2023 Chenglei Si, Dan Friedman, Nitish Joshi, Shi Feng, Danqi Chen, He He

We investigate the inductive biases of ICL from the perspective of feature bias: which feature ICL is more likely to use given a set of underspecified demonstrations in which two features are equally predictive of the labels.

In-Context Learning Inductive Bias

How do decoding algorithms distribute information in dialogue responses?

no code implementations29 Mar 2023 Saranya Venkatraman, He He, David Reitter

We find that (i) surprisingly, model-generated responses follow the UID principle to a greater extent than human responses, and (ii) decoding algorithms that promote UID do not generate higher-quality responses.

Dialogue Generation

Extrapolative Controlled Sequence Generation via Iterative Refinement

1 code implementation8 Mar 2023 Vishakh Padmakumar, Richard Yuanzhe Pang, He He, Ankur P. Parikh

We study the problem of extrapolative controlled generation, i. e., generating sequences with attribute values beyond the range seen in training.

Attribute Drug Discovery +1

Reward Gaming in Conditional Text Generation

no code implementations16 Nov 2022 Richard Yuanzhe Pang, Vishakh Padmakumar, Thibault Sellam, Ankur P. Parikh, He He

To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations.

Conditional Text Generation Reinforcement Learning (RL)

Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing

1 code implementation25 Oct 2022 Tuhin Chakrabarty, Vishakh Padmakumar, He He

The core component of our system is a language model fine-tuned on a diverse collection of instructions for poetry writing.

Language Modelling Sentence

Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens

1 code implementation25 Oct 2022 Nitish Joshi, Xiang Pan, He He

In case (i), we want the model to be invariant to the feature, which is neither necessary nor sufficient for prediction.


Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining

1 code implementation10 Oct 2022 Asa Cooper Stickland, Sailik Sengupta, Jason Krone, Saab Mansour, He He

To benchmark the performance of pretrained multilingual language models, we construct noisy datasets covering five languages and four NLP tasks and observe a clear gap in the performance between clean and noisy data in the zero-shot cross-lingual setting.

Data Augmentation Pretrained Multilingual Language Models +1

Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation

no code implementations4 Oct 2022 Aahlad Puli, Nitish Joshi, He He, Rajesh Ranganath

In prediction tasks, there exist features that are related to the label in the same way across different settings for that task; these are semantic features or semantics.

Data Augmentation Natural Language Inference

Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought

1 code implementation3 Oct 2022 Abulhair Saparov, He He

Large language models (LLMs) have shown remarkable reasoning capabilities given chain-of-thought prompts (examples with intermediate reasoning steps).

Mathematical Reasoning Question Answering +1

On the Relation between Sensitivity and Accuracy in In-context Learning

1 code implementation16 Sep 2022 Yanda Chen, Chen Zhao, Zhou Yu, Kathleen McKeown, He He

In-context learning (ICL) suffers from oversensitivity to the prompt, making it unreliable in real-world scenarios.

In-Context Learning Relation

Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning

no code implementations NAACL 2022 Vishakh Padmakumar, Leonard Lausen, Miguel Ballesteros, Sheng Zha, He He, George Karypis

Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks.

Multi-Task Learning Representation Learning

Amortized Noisy Channel Neural Machine Translation

no code implementations16 Dec 2021 Richard Yuanzhe Pang, He He, Kyunghyun Cho

For all three approaches, the generated translations fail to achieve rewards comparable to BSR, but the translation quality approximated by BLEU and BLEURT is similar to the quality of BSR-produced translations.

Imitation Learning Knowledge Distillation +4

QuALITY: Question Answering with Long Input Texts, Yes!

2 code implementations NAACL 2022 Richard Yuanzhe Pang, Alicia Parrish, Nitish Joshi, Nikita Nangia, Jason Phang, Angelica Chen, Vishakh Padmakumar, Johnny Ma, Jana Thompson, He He, Samuel R. Bowman

To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5, 000 tokens, much longer than typical current models can process.

Multiple-choice Multiple Choice Question Answering (MCQA)

Machine-in-the-Loop Rewriting for Creative Image Captioning

1 code implementation NAACL 2022 Vishakh Padmakumar, He He

Machine-in-the-loop writing aims to enable humans to collaborate with models to complete their writing tasks more effectively.

Descriptive Image Captioning +2

SeqPATE: Differentially Private Text Generation via Knowledge Distillation

no code implementations29 Sep 2021 Zhiliang Tian, Yingxiu Zhao, Ziyue Huang, Yu-Xiang Wang, Nevin Zhang, He He

Differentially private (DP) learning algorithms provide guarantees on identifying the existence of a training sample from model outputs.

Knowledge Distillation Sentence +2

Types of Out-of-Distribution Texts and How to Detect Them

1 code implementation EMNLP 2021 Udit Arora, William Huang, He He

Despite agreement on the importance of detecting out-of-distribution (OOD) examples, there is little consensus on the formal definition of OOD examples and how to best detect them.

Density Estimation Language Modelling +2

An Investigation of the (In)effectiveness of Counterfactually Augmented Data

1 code implementation ACL 2022 Nitish Joshi, He He

While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data.

Natural Language Understanding

Unsupervised Extractive Summarization using Pointwise Mutual Information

1 code implementation EACL 2021 Vishakh Padmakumar, He He

Unsupervised approaches to extractive summarization usually rely on a notion of sentence importance defined by the semantic similarity between a sentence and the document.

Extractive Summarization Language Modelling +4

Text Generation by Learning from Demonstrations

1 code implementation ICLR 2021 Richard Yuanzhe Pang, He He

Current approaches to text generation largely rely on autoregressive models and maximum likelihood estimation.

Machine Translation Question Generation +4

An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models

1 code implementation14 Jul 2020 Lifu Tu, Garima Lalwani, Spandana Gella, He He

Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset.

Multi-Task Learning Natural Language Inference +1

Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach

1 code implementation3 Dec 2019 He He, Dongrui Wu

Currently, most domain adaptation approaches require the source domains to have the same feature space and label space as the target domain, which limits their applications, as the auxiliary data may have different feature spaces and/or different label spaces.

Domain Adaptation Motor Imagery +1

A Dynamic Strategy Coach for Effective Negotiation

no code implementations WS 2019 Yiheng Zhou, He He, Alan W. black, Yulia Tsvetkov

We consider a bargaining scenario where a seller and a buyer negotiate the price of an item for sale through a text-based dialog.

Decision Making Text Generation

Multi-View Broad Learning System for Primate Oculomotor Decision Decoding

1 code implementation16 Aug 2019 Zhenhua Shi, Xiaomo Chen, Changming Zhao, He He, Veit Stuphorn, Dongrui Wu

Multi-view learning improves the learning performance by utilizing multi-view data: data collected from multiple sources, or feature sets extracted from the same data source.


GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

3 code implementations9 Jul 2019 Jian Guo, He He, Tong He, Leonard Lausen, Mu Li, Haibin Lin, Xingjian Shi, Chenguang Wang, Junyuan Xie, Sheng Zha, Aston Zhang, Hang Zhang, Zhi Zhang, Zhongyue Zhang, Shuai Zheng, Yi Zhu

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).

Pun Generation with Surprise

2 code implementations NAACL 2019 He He, Nanyun Peng, Percy Liang

We tackle the problem of generating a pun sentence given a pair of homophones (e. g., "died" and "dyed").

Language Modelling Sentence +1

Quizbowl: The Case for Incremental Question Answering

no code implementations9 Apr 2019 Pedro Rodriguez, Shi Feng, Mohit Iyyer, He He, Jordan Boyd-Graber

Throughout this paper, we show that collaborations with the vibrant trivia community have contributed to the quality of our dataset, spawned new research directions, and doubled as an exciting way to engage the public with research in machine learning and natural language processing.

BIG-bench Machine Learning Decision Making +1

QuAC: Question Answering in Context

no code implementations EMNLP 2018 Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer

We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total).

Question Answering Reading Comprehension

QuAC : Question Answering in Context

no code implementations21 Aug 2018 Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer

We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total).

Question Answering Reading Comprehension

Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach

1 code implementation8 Aug 2018 He He, Dongrui Wu

Our approach has three desirable properties: 1) it aligns the EEG trials directly in the Euclidean space, and any signal processing, feature extraction and machine learning algorithms can then be applied to the aligned trials; 2) its computational cost is very low; and, 3) it is unsupervised and does not need any label information from the new subject.

EEG General Classification +2

Transfer Learning Enhanced Common Spatial Pattern Filtering for Brain Computer Interfaces (BCIs): Overview and a New Approach

no code implementations8 Aug 2018 He He, Dongrui Wu

The electroencephalogram (EEG) is the most widely used input for brain computer interfaces (BCIs), and common spatial pattern (CSP) is frequently used to spatially filter it to increase its signal-to-noise ratio.

EEG General Classification +2

Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer

6 code implementations NAACL 2018 Juncen Li, Robin Jia, He He, Percy Liang

We consider the task of text attribute transfer: transforming a sentence to alter a specific attribute (e. g., sentiment) while preserving its attribute-independent content (e. g., changing "screen is just the right size" to "screen is too small").

Attribute Image Captioning +4

Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings

2 code implementations ACL 2017 He He, Anusha Balakrishnan, Mihail Eric, Percy Liang

To model both structured knowledge and unstructured language, we propose a neural model with dynamic knowledge graph embeddings that evolve as the dialogue progresses.

Knowledge Graph Embeddings

Opponent Modeling in Deep Reinforcement Learning

1 code implementation18 Sep 2016 He He, Jordan Boyd-Graber, Kevin Kwok, Hal Daumé III

Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because strategies interact with each other and change.

reinforcement-learning Reinforcement Learning (RL)

Active Information Acquisition

no code implementations5 Feb 2016 He He, Paul Mineiro, Nikos Karampatziakis

We propose a general framework for sequential and dynamic acquisition of useful information in order to solve a particular task.

General Reinforcement Learning Reinforcement Learning (RL) +1

Learning to Search for Dependencies

no code implementations18 Mar 2015 Kai-Wei Chang, He He, Hal Daumé III, John Langford

We demonstrate that a dependency parser can be built using a credit assignment compiler which removes the burden of worrying about low-level machine learning details from the parser implementation.

BIG-bench Machine Learning

Learning to Search in Branch and Bound Algorithms

no code implementations NeurIPS 2014 He He, Hal Daume III, Jason M. Eisner

Branch-and-bound is a widely used method in combinatorial optimization, including mixed integer programming, structured prediction and MAP inference.

Combinatorial Optimization Imitation Learning +1

A Credit Assignment Compiler for Joint Prediction

no code implementations NeurIPS 2016 Kai-Wei Chang, He He, Hal Daumé III, John Langford, Stephane Ross

Many machine learning applications involve jointly predicting multiple mutually dependent output variables.

Imitation Learning by Coaching

no code implementations NeurIPS 2012 He He, Jason Eisner, Hal Daume

However, it is important to note that these guarantees depend on how well the policy we found can imitate the oracle on the training data.

feature selection Imitation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.