Search Results for author:
Found 11 papers, 6 papers with code
Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models
This approach utilizes contrastive learning to align representations of in-context examples across different positions and introduces a consistency loss to ensure similar representations for inputs with different permutations.
Counterfactual Generation with Identifiability Guarantees
In this work, we tackle the domain-varying dependence between the content and the style variables inherent in the counterfactual generation task.
Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning
While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems without access to external resources.
The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis
Understanding in-context learning (ICL) capability that enables large language models (LLMs) to excel in proficiency through demonstration examples is of utmost importance.
Explainable Recommender with Geometric Information Bottleneck
Explainable recommender systems can explain their recommendation decisions, enhancing user trust in the systems.
Distinguishability Calibration to In-Context Learning
When using prompt-based learning for text classification, the goal is to use a pre-trained language model (PLM) to predict a missing token in a pre-defined template given an input text, which can be mapped to a class label.
Tracking Brand-Associated Polarity-Bearing Topics in User Reviews
Monitoring online customer reviews is important for business organisations to measure customer satisfaction and better manage their reputations.
Addressing Token Uniformity in Transformers via Singular Value Transformation
In this paper, we propose to use the distribution of singular values of outputs of each transformer layer to characterise the phenomenon of token uniformity and empirically illustrate that a less skewed singular value distribution can alleviate the `token uniformity' problem.
Hierarchical Interpretation of Neural Text Classification
Neural models developed in NLP however often compose word semantics in a hierarchical manner and text classification requires hierarchical modelling to aggregate local information in order to deal with topic and label shifts more effectively.
Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction
To investigate the degree of reliance of existing ECE models on clause relative positions, we propose a novel strategy to generate adversarial examples in which the relative position information is no longer the indicative feature of cause clauses.
LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification
The generator learns to generate examples to attack the classifier while the classifier learns to defend these attacks.
