Search Results for author:
Found 38 papers, 24 papers with code
Direct Preference Optimization Using Sparse Feature-Level Constraints
The alignment of large language models (LLMs) with human preferences remains a key challenge.
CycleResearcher: Improving Automated Research via Automated Review
In research, the papers generated by the CycleResearcher model achieved a score of 5. 36 in simulated peer reviews, surpassing the preprint level of 5. 24 from human experts and approaching the accepted paper level of 5. 69.
CAP: Data Contamination Detection via Consistency Amplification
Additionally, CAP is applicable to various benchmarks and works for both white-box and black-box models.
Locking Down the Finetuned LLMs Safety
SafetyLock leverages our discovery that fine-tuned models retain similar safety-related activation representations to their base models.
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Inspired by the success of OpenAI's o1 model, which demonstrated improved reasoning abilities through step-by-step reasoning and reinforcement learning, OpenR integrates test-time compute, reinforcement learning, and process supervision to improve reasoning in LLMs.
Personality Alignment of Large Language Models
This dataset allows us to quantitatively evaluate the extent to which LLMs can align with each subject's behavioral patterns.
CulturePark: Boosting Cross-cultural Understanding in Large Language Models
Cultural bias is pervasive in many large language models (LLMs), largely due to the deficiency of data representative of different cultures.
A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution
Based on Pre-trained Language Models (PLMs), event coreference resolution (ECR) systems have demonstrated outstanding performance in clustering coreferential events across documents.
Detoxifying Large Language Models via Knowledge Editing
This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs).
How Likely Do LLMs with CoT Mimic Human Reasoning?
Chain-of-thought emerges as a promising technique for eliciting reasoning capabilities from Large Language Models (LLMs).
Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark
Although previous counterfactual QA benchmarks can separate the internal memory of LLMs, they focus solely on final QA performance, which is insufficient for reporting LLMs' real reasoning abilities.
GenDec: A robust generative Question-decomposition method for Multi-hop reasoning
Multi-hop QA (MHQA) involves step-by-step reasoning to answer complex questions and find multiple relevant supporting facts.
Supervised Knowledge Makes Large Language Models Better In-context Learners
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering.
Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity
This survey addresses the crucial issue of factuality in Large Language Models (LLMs).
Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks.
A Survey on Evaluation of Large Language Models
Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications.
Masked conditional variational autoencoders for chromosome straightening
This yields a non-trivial reconstruction task, allowing the model to effectively preserve chromosome banding patterns and structure details in the reconstructed results.
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
To ensure the reliability of PandaLM, we collect a diverse human-annotated test dataset, where all contexts are generated by humans and labels are aligned with human preferences.
PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
Furthermore, we present a comprehensive analysis to understand the mystery behind prompt robustness and its transferability.
Cross-Lingual Paraphrase Identification
Machine Translation
+5
Out-of-Distribution Generalization in Text Classification: Past, Present, and Future
Machine learning (ML) systems in natural language processing (NLP) face significant challenges in generalizing to out-of-distribution (OOD) data, where the test distribution differs from the training data distribution.
MAGE: Machine-generated Text Detection in the Wild
In practical scenarios, however, the detector faces texts from various domains or LLMs without knowing their sources.
Measuring Consistency in Text-based Financial Forecasting Models
Using FinTrust, we show that the consistency of state-of-the-art NLP models for financial forecasting is poor.
Learning to Generalize for Cross-domain QA
Our method has been theoretically and empirically shown to be effective in enhancing the generalization ability of both generative and discriminative models.
On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective
In this paper, we conduct a thorough evaluation of the robustness of ChatGPT from the adversarial and out-of-distribution (OOD) perspective.
Exploiting Rich Textual User-Product Context for Improving Sentiment Analysis
User and product information associated with a review is useful for sentiment polarity prediction.
GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective
Pre-trained language models (PLMs) are known to improve the generalization performance of natural language understanding models by leveraging large amounts of data during the pre-training phase.
Natural Language Understanding
Out-of-Distribution Generalization
Pre-Training a Graph Recurrent Network for Language Representation
Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing.
FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition
Few-shot Named Entity Recognition (NER) is imperative for entity tagging in limited resource domains and thus received proper attention in recent years.
USB: A Unified Semi-supervised Learning Benchmark for Classification
We further provide the pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning.
Towards Fine-grained Causal Reasoning and QA
Understanding causality is key to the success of NLP applications, especially in high-stakes domains.
Challenges for Open-domain Targeted Sentiment Analysis
Since previous studies on open-domain targeted sentiment analysis are limited in dataset domain variety and sentence level, we propose a novel dataset consisting of 6, 013 human-labeled data to extend the data domains in topics of interest and document level.
A Rationale-Centric Framework for Human-in-the-loop Machine Learning
We present a novel rationale-centric framework with human-in-the-loop -- Rationales-centric Double-robustness Learning (RDL) -- to boost model out-of-distribution performance in few-shot learning scenarios.
NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-task Financial Forecasting
Financial forecasting has been an important and active area of machine learning research because of the challenges it presents and the potential rewards that even minor improvements in prediction accuracy or forecasting may entail.
Fact Check: Analyzing Financial Events from Multilingual News Sources
The explosion in the sheer magnitude and complexity of financial news data in recent years makes it increasingly challenging for investment analysts to extract valuable insights and perform analysis.
Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis
While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that may exist in their training and test data.
Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification
Corporate mergers and acquisitions (M&A) account for billions of dollars of investment globally every year, and offer an interesting and challenging domain for artificial intelligence.
Explainable Text-Driven Neural Network for Stock Prediction
It has been shown that financial news leads to the fluctuation of stock prices.
