Search Results for author:
Found 25 papers, 11 papers with code
Analytical Reasoning of Text
In this paper, we study the challenge of analytical reasoning of text and collect a new dataset consisting of questions from the Law School Admission Test from 1991 to 2016.
Deep Learning and Large Language Models for Audio and Text Analysis in Predicting Suicidal Acts in Chinese Psychological Support Hotlines
Surprisingly, the proposed simple LLM pipeline achieved strong performance on a test set of 46 subjects, with an F1 score of 76\% when combined with manual scale rating.
An Exploratory Deep Learning Approach for Predicting Subsequent Suicidal Acts in Chinese Psychological Support Hotlines
Psychological support hotlines are an effective suicide prevention measure that typically relies on professionals using suicide risk assessment scales to predict individual risk scores.
Prover-Verifier Games improve legibility of LLM outputs
One way to increase confidence in the outputs of Large Language Models (LLMs) is to support them with reasoning that is clear and easy to check -- a property we call legibility.
Fine-grained Speech Sentiment Analysis in Chinese Psychological Support Hotlines Based on Large-scale Pre-trained Model
However, the high demand for psychological interventions often results in a shortage of professional operators, highlighting the need for an effective speech emotion recognition model.
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate whether a model faithfully followed instructions or generated safe outputs.
Zero-shot causal learning
There are a large number of methods to predict the effect of an existing intervention based on historical data from individuals who received it.
Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting
(2) How to cohere with context and preserve the knowledge when generating a stylized response.
Statistically Meaningful Approximation: a Theoretical Analysis for Approximating Turing Machines with Transformers
A common lens to theoretically study neural net architectures is to analyze the functions they can approximate.
Learning Neural Templates for Recommender Dialogue System
Second, only the items mentioned in the training corpus have a chance to be recommended in the conversation.
Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers
A common lens to theoretically study neural net architectures is to analyze the functions they can approximate.
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
Domain generalization aims at performing well on unseen test environments with data from a limited number of training environments.
Maria: A Visual Experience Powered Conversational Agent
The retriever aims to retrieve a correlated image to the dialog from an image index, while the visual concept detector extracts rich visual knowledge from the image.
ChemistryQA: A Complex Question Answering Dataset from Chemistry
We notice that some real-world QA tasks are more complex, which cannot be solved by end-to-end neural networks or translated to any kind of formal representations.
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
Self-training algorithms, which train a model to fit pseudolabels predicted by another previously-learned model, have been very successful for learning with unlabeled data using neural networks.
Table2Charts: Recommending Charts by Learning Shared Table Representations
It is common for people to create different types of charts to explore a multi-dimensional dataset (table).
Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization
Real-world large-scale datasets are heteroskedastic and imbalanced -- labels have varying levels of uncertainty and label distributions are long-tailed.
Ranked #11 on
Image Classification
on WebVision-1000
Active Online Learning with Hidden Shifting Domains
We propose a surprisingly simple algorithm that adaptively balances its regret and its number of label queries in settings where the data streams are from a mixture of hidden domains.
Self-training Avoids Using Spurious Features Under Domain Shift
In unsupervised domain adaptation, existing theory focuses on situations where the source and target domains are close.
Active Online Domain Adaptation
We propose a surprisingly simple algorithm that adaptively balances its regret and its number of label queries in settings where the data streams are from a mixture of hidden domains.
Experience Augmentation: Boosting and Accelerating Off-Policy Multi-Agent Reinforcement Learning
We demonstrate our approach by combining it with MADDPG and verifing the performance in two homogeneous and one heterogeneous environments.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
A random forest based approach for predicting spreads in the primary catastrophe bond market
The random forest shows an impressive predictive power on unseen primary catastrophe bond data explaining 93% of the total variability.
BERT-AL: BERT for Arbitrarily Long Document Understanding
When we apply BERT to long text tasks, e. g., document-level text summarization: 1) Truncating inputs by the maximum sequence length will decrease performance, since the model cannot capture long dependency and global information ranging the whole document.
Weakly Supervised Disentanglement with Guarantees
Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning.
Recurrent Neural Networks as Weighted Language Recognizers
We investigate the computational complexity of various problems for simple recurrent neural networks (RNNs) as formal models for recognizing weighted languages.
