Search Results for author: Shi Feng

Found 60 papers, 26 papers with code

Human-Centered Evaluation of Explanations

no code implementations NAACL (ACL) 2022 Jordan Boyd-Graber, Samuel Carton, Shi Feng, Q. Vera Liao, Tania Lombrozo, Alison Smith-Renner, Chenhao Tan

The NLP community are increasingly interested in providing explanations for NLP models to help people make sense of model behavior and potentially improve human interaction with models.

Spontaneous Reward Hacking in Iterative Self-Refinement

no code implementations5 Jul 2024 Jane Pan, He He, Samuel R. Bowman, Shi Feng

Language models are capable of iteratively improving their outputs based on natural language feedback, thus enabling in-context optimization of user preference.

Language Modelling

A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models

1 code implementation2 Jul 2024 Daking Rai, Yilun Zhou, Shi Feng, Abulhair Saparov, Ziyu Yao

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations.

Navigate

A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation

1 code implementation14 Jun 2024 Yongkang Liu, Ercong Nie, Shi Feng, Zheng Hua, Zifeng Ding, Daling Wang, Yifei Zhang, Hinrich Schütze

We conduct experiments on Chinese dialogue datasets from five different domains and show that AMD$^2$G achieves superior performance compared to both direct training on the target domain corpus and collective training on all five domain corpora.

Data Augmentation Dialogue Generation +1

ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models

no code implementations15 May 2024 Siwei Wang, Yifei Shen, Shi Feng, Haoran Sun, Shang-Hua Teng, Wei Chen

In this paper, we present the findings of our Project ALPINE which stands for ``Autoregressive Learning for Planning In NEtworks."

Application of Kalman Filter in Stochastic Differential Equations

no code implementations21 Apr 2024 Wencheng Bao, Shi Feng, Kaiwen Zhang

In areas such as finance, engineering, and science, we often face situations that change quickly and unpredictably.

LLM Evaluators Recognize and Favor Their Own Generations

no code implementations15 Apr 2024 Arjun Panickssery, Samuel R. Bowman, Shi Feng

Self-evaluation using large language models (LLMs) has proven valuable not only in benchmarking but also methods like reward modeling, constitutional AI, and self-refinement.

Benchmarking

A Correction of Pseudo Log-Likelihood Method

no code implementations26 Mar 2024 Shi Feng, Nuoya Xiong, Zhijie Zhang, Wei Chen

Pseudo log-likelihood is a type of maximum likelihood estimation (MLE) method used in various fields including contextual bandits, influence maximization of social networks, and causal bandits.

Multi-Armed Bandits

FEEL: A Framework for Evaluating Emotional Support Capability with Large Language Models

1 code implementation23 Mar 2024 Huaiwen Zhang, Yu Chen, Ming Wang, Shi Feng

Emotional Support Conversation (ESC) is a typical dialogue that can effectively assist the user in mitigating emotional pressures.

Ensemble Learning

Is Mamba Effective for Time Series Forecasting?

1 code implementation17 Mar 2024 Zihan Wang, Fanheng Kong, Shi Feng, Ming Wang, Xiaocui Yang, Han Zhao, Daling Wang, Yifei Zhang

For TSF tasks, these characteristics enable Mamba to comprehend hidden patterns as the Transformer and reduce computational overhead compared to the Transformer.

Computational Efficiency Time Series +1

KARL: Knowledge-Aware Retrieval and Representations aid Retention and Learning in Students

no code implementations19 Feb 2024 Matthew Shu, Nishant Balepur, Shi Feng, Jordan Boyd-Graber

Flashcard schedulers are tools that rely on 1) student models to predict the flashcards a student knows; and 2) teaching policies to schedule cards based on these predictions.

Knowledge Tracing Retrieval +1

HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy

1 code implementation26 Jan 2024 Yongkang Liu, Yiqun Zhang, Qian Li, Tong Liu, Shi Feng, Daling Wang, Yifei Zhang, Hinrich Schütze

As LMs grow in size, fine-tuning the full parameters of LMs requires a prohibitively large amount of GPU memory.

STICKERCONV: Generating Multimodal Empathetic Responses from Scratch

1 code implementation20 Jan 2024 Yiqun Zhang, Fanheng Kong, Peidong Wang, Shuang Sun, Lingshuai Wang, Shi Feng, Daling Wang, Yifei Zhang, Kaisong Song

Stickers, while widely recognized for enhancing empathetic communication in online interactions, remain underexplored in current empathetic dialogue research, notably due to the challenge of a lack of comprehensive datasets.

2k Empathetic Response Generation +1

Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong

no code implementations19 Oct 2023 Chenglei Si, Navita Goyal, Sherry Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daumé III, Jordan Boyd-Graber

To reduce over-reliance on LLMs, we ask LLMs to provide contrastive information - explain both why the claim is true and false, and then we present both sides of the explanation to users.

Fact Checking Information Retrieval

MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks

2 code implementations13 Oct 2023 Xiaocui Yang, Wenfang Wu, Shi Feng, Ming Wang, Daling Wang, Yang Li, Qi Sun, Yifei Zhang, XiaoMing Fu, Soujanya Poria

Consequently, our work complements research on the performance of MLLMs in multimodal comprehension tasks, achieving a more comprehensive and holistic evaluation of MLLMs.

Multimodal Reasoning

Machine learning assist nyc subway navigation safer and faster

no code implementations3 Oct 2023 Wencheng Bao, Shi Feng

Mainstream navigation software, like Google and Apple Maps, often lacks the ability to provide routes prioritizing safety.

Machine learning reveals features of spinon Fermi surface

no code implementations5 Jun 2023 Kevin Zhang, Shi Feng, Yuri D. Lensky, Nandini Trivedi, Eun-Ah Kim

With rapid progress in simulation of strongly interacting quantum Hamiltonians, the challenge in characterizing unknown phases becomes a bottleneck for scientific progress.

Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response

no code implementations24 May 2023 Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang, Hinrich Schütze

There are risks in using eference-free evaluators based on LLMs to evaluate the quality of dialogue responses.

Dialogue Generation

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

Learning Human-Compatible Representations for Case-Based Decision Support

1 code implementation6 Mar 2023 Han Liu, Yizhou Tian, Chacha Chen, Shi Feng, Yuxin Chen, Chenhao Tan

Despite the promising performance of supervised learning, representations learned by supervised models may not align well with human intuitions: what models consider as similar examples can be perceived as distinct by humans.

Classification Decision Making +1

Combinatorial Causal Bandits without Graph Skeleton

1 code implementation31 Jan 2023 Shi Feng, Nuoya Xiong, Wei Chen

This paper studies the CCB problem without the graph structure on binary general causal models and BGLMs.

Few-shot Multimodal Sentiment Analysis based on Multimodal Probabilistic Fusion Prompts

1 code implementation12 Nov 2022 Xiaocui Yang, Shi Feng, Daling Wang, Pengfei Hong, Soujanya Poria

To tackle this problem, we propose a novel method called Multimodal Probabilistic Fusion Prompts (MultiPoint) that leverages diverse cues from different modalities for multimodal sentiment detection in the few-shot scenario.

Language Modelling Multimodal Sentiment Analysis

Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive Learning

1 code implementation8 Nov 2022 Qian Li, Shafiq Joty, Daling Wang, Shi Feng, Yifei Zhang

Sparsity of formal knowledge and roughness of non-ontological construction make sparsity problem particularly prominent in Open Knowledge Graphs (OpenKGs).

Contrastive Learning Knowledge Graphs +1

Active Example Selection for In-Context Learning

1 code implementation8 Nov 2022 Yiming Zhang, Shi Feng, Chenhao Tan

For GPT-2, our learned policies demonstrate strong abilities of generalizing to unseen tasks in training, with a $5. 8\%$ improvement on average.

In-Context Learning

DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection

no code implementations25 Oct 2022 Yongkang Liu, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms.

Retrieval

MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation

1 code implementation COLING 2022 Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang

Building dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such as GPT-3 and T5.

Data Augmentation Dialogue Generation

Combinatorial Causal Bandits

1 code implementation4 Jun 2022 Shi Feng, Wei Chen

For the special case of linear models with hidden variables, we apply causal inference techniques such as the do-calculus to convert the original model into a Markovian model, and then show that our BGLM-OFU algorithm and another algorithm based on the linear regression both solve such linear models with hidden variables.

Causal Inference

Machine Explanations and Human Understanding

1 code implementation8 Feb 2022 Chacha Chen, Shi Feng, Amit Sharma, Chenhao Tan

Our key result is that without assumptions about task-specific intuitions, explanations may potentially improve human understanding of model decision boundary, but they cannot improve human understanding of task decision boundary or model error.

Decision Making Open-Ended Question Answering

Multimodal Sentiment Detection Based on Multi-channel Graph Neural Networks

1 code implementation ACL 2021 Xiaocui Yang, Shi Feng, Yifei Zhang, Daling Wang

In this paper, we propose Multi-channel Graph Neural Networks with Sentiment-awareness (MGNNS) for image-text sentiment detection.

Calibrate Before Use: Improving Few-Shot Performance of Language Models

5 code implementations19 Feb 2021 Tony Z. Zhao, Eric Wallace, Shi Feng, Dan Klein, Sameer Singh

We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order of the training examples can cause accuracy to vary from near chance to near state-of-the-art.

Few-Shot Learning

Concealed Data Poisoning Attacks on NLP Models

no code implementations NAACL 2021 Eric Wallace, Tony Z. Zhao, Shi Feng, Sameer Singh

In this work, we develop a new data poisoning attack that allows an adversary to control model predictions whenever a desired trigger phrase is present in the input.

Data Poisoning Language Modelling +2

How Pre-trained Word Representations Capture Commonsense Physical Comparisons

no code implementations WS 2019 Pranav Goel, Shi Feng, Jordan Boyd-Graber

One type of common sense is how two objects compare on physical properties such as size and weight: e. g., {`}is a house bigger than a person?{'}.

Common Sense Reasoning

Answer-Supervised Question Reformulation for Enhancing Conversational Machine Comprehension

no code implementations WS 2019 Qian Li, Hui Su, Cheng Niu, Daling Wang, Zekang Li, Shi Feng, Yifei Zhang

Moreover, pretraining is essential in reinforcement learning models, so we provide a high-quality annotated dataset for question reformulation by sampling a part of QuAC dataset.

Reading Comprehension reinforcement-learning +2

Universal Adversarial Triggers for Attacking and Analyzing NLP

1 code implementation IJCNLP 2019 Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, Sameer Singh

We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a model to produce a specific prediction when concatenated to any input from a dataset.

Language Modelling Reading Comprehension

Misleading Failures of Partial-input Baselines

no code implementations ACL 2019 Shi Feng, Eric Wallace, Jordan Boyd-Graber

Recent work establishes dataset difficulty and removes annotation artifacts via partial-input baselines (e. g., hypothesis-only models for SNLI or question-only models for VQA).

Natural Language Inference Visual Question Answering (VQA)

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

Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation

1 code implementation1 Feb 2019 Sahil Singla, Eric Wallace, Shi Feng, Soheil Feizi

Second, we compute the importance of group-features in deep learning interpretation by introducing a sparsity regularization term.

Feature Importance General Classification

What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play

no code implementations23 Oct 2018 Shi Feng, Jordan Boyd-Graber

Machine learning is an important tool for decision making, but its ethical and responsible application requires rigorous vetting of its interpretability and utility: an understudied problem, particularly for natural language processing models.

BIG-bench Machine Learning Decision Making +1

Personalized Microblog Sentiment Classification via Adversarial Cross-lingual Multi-task Learning

no code implementations EMNLP 2018 Weichao Wang, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

Then the attention-based CNN model is incorporated into a novel adversarial cross-lingual learning framework, in which with the help of user properties as bridge between languages, we can extract the language-specific features and language-independent features to enrich the user post representation so as to alleviate the data insufficiency problem.

General Classification Multi-Task Learning +2

Pathologies of Neural Models Make Interpretations Difficult

no code implementations EMNLP 2018 Shi Feng, Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez, Jordan Boyd-Graber

In existing interpretation methods for NLP, a word's importance is determined by either input perturbation---measuring the decrease in model confidence when that word is removed---or by the gradient with respect to that word.

Sentence

Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation

no code implementations COLING 2016 Shi Feng, Shujie Liu, Nan Yang, Mu Li, Ming Zhou, Kenny Q. Zhu

In neural machine translation, the attention mechanism facilitates the translation process by producing a soft alignment between the source sentence and the target sentence.

Decoder Machine Translation +2

Implicit Distortion and Fertility Models for Attention-based Encoder-Decoder NMT Model

no code implementations13 Jan 2016 Shi Feng, Shujie Liu, Mu Li, Ming Zhou

Aiming to resolve these problems, we propose new variations of attention-based encoder-decoder and compare them with other models on machine translation.

Attribute Decoder +6

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