Search Results for author:
Found 23 papers, 12 papers with code
A Law of Next-Token Prediction in Large Language Models
Large language models (LLMs) have been widely employed across various application domains, yet their black-box nature poses significant challenges to understanding how these models process input data internally to make predictions.
An Empirical Analysis on Large Language Models in Debate Evaluation
In this study, we investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3. 5 and GPT-4 in the context of debate evaluation.
Unveiling Divergent Inductive Biases of LLMs on Temporal Data
Unraveling the intricate details of events in natural language necessitates a subtle understanding of temporal dynamics.
SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation
Existing reference-free reasoning evaluation metrics, while eliminating the need for human-crafted reasoning chains as references, often require fine-tuning with human-derived chains before evaluation, complicating the process and questioning their adaptability to other datasets.
On Regularization and Inference with Label Constraints
Prior knowledge and symbolic rules in machine learning are often expressed in the form of label constraints, especially in structured prediction problems.
Rethinking with Retrieval: Faithful Large Language Model Inference
To address this issue, we propose a novel post-processing approach, rethinking with retrieval (RR), which retrieves relevant external knowledge based on the decomposed reasoning steps obtained from the chain-of-thought (CoT) prompting.
Ranked #2 on
Question Answering
on StrategyQA
A Law of Data Separation in Deep Learning
While deep learning has enabled significant advances in many areas of science, its black-box nature hinders architecture design for future artificial intelligence applications and interpretation for high-stakes decision makings.
Weighted Training for Cross-Task Learning
In this paper, we introduce Target-Aware Weighted Training (TAWT), a weighted training algorithm for cross-task learning based on minimizing a representation-based task distance between the source and target tasks.
Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training
More importantly, when moving to the imbalanced case, our analysis of the Layer-Peeled Model reveals a hitherto unknown phenomenon that we term \textit{Minority Collapse}, which fundamentally limits the performance of deep learning models on the minority classes.
PABI: A Unified PAC-Bayesian Informativeness Measure for Incidental Supervision Signals
Real-world applications often require making use of {\em a range of incidental supervision signals}.
QANom: Question-Answer driven SRL for Nominalizations
We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom.
Toward Better Generalization Bounds with Locally Elastic Stability
Given that, we propose \emph{locally elastic stability} as a weaker and distribution-dependent stability notion, which still yields exponential generalization bounds.
Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity
As a popular approach to modeling the dynamics of training overparametrized neural networks (NNs), the neural tangent kernels (NTK) are known to fall behind real-world NNs in generalization ability.
Towards Understanding the Dynamics of the First-Order Adversaries
An acknowledged weakness of neural networks is their vulnerability to adversarial perturbations to the inputs.
Understanding Spatial Relations through Multiple Modalities
Recognizing spatial relations and reasoning about them is essential in multiple applications including navigation, direction giving and human-computer interaction in general.
Foreseeing the Benefits of Incidental Supervision
Real-world applications often require improved models by leveraging a range of cheap incidental supervision signals.
Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic
This paper proposes SplitSGD, a new dynamic learning rate schedule for stochastic optimization.
The Local Elasticity of Neural Networks
This phenomenon is shown to persist for neural networks with nonlinear activation functions through extensive simulations on real-life and synthetic datasets, whereas this is not observed in linear classifiers.
QuASE: Question-Answer Driven Sentence Encoding
Question-answering (QA) data often encodes essential information in many facets.
Partial Or Complete, That's The Question
For many structured learning tasks, the data annotation process is complex and costly.
Neural Networks for Negation Cue Detection in Chinese
In particular, the use of a character-based model allows us to capture characteristics of negation cues in Chinese using word-embedding information only.
Detecting negation scope is easy, except when it isn't
Several corpora have been annotated with negation scope{---}the set of words whose meaning is negated by a cue like the word {``}not{''}{---}leading to the development of classifiers that detect negation scope with high accuracy.
F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media
We focus on named entity recognition (NER) for Chinese social media.
