Search Results for author:
Found 20 papers, 12 papers with code
XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts
We introduce XFT, a simple yet powerful training scheme, by simply merging upcycled Mixture-of-Experts (MoE) to unleash the performance limit of instruction-tuned code Large Language Models (LLMs).
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
Pretrained language models underpin several AI applications, but their high computational cost for training limits accessibility.
StarCoder 2 and The Stack v2: The Next Generation
Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size.
Ranked #25 on
Code Generation
on MBPP
Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models
Through investigations across 5 tasks and 8 different datasets encompassing both code comprehension and code generation tasks, we find that FFT generally leads to the best downstream performance across all scales, and PEFT methods differ significantly in their efficacy based on the model scale.
Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?
Each scenario in the corpus is annotated with a complete IRAC analysis in a semi-structured format so that both machines and legal professionals are able to interpret and understand the annotations.
Fake News Detectors are Biased against Texts Generated by Large Language Models
The spread of fake news has emerged as a critical challenge, undermining trust and posing threats to society.
Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?
The correctness and unambiguity of API usage among these code models are crucial for achieving desirable program functionalities, requiring them to learn various API fully qualified names structurally and semantically.
OctoPack: Instruction Tuning Code Large Language Models
We benchmark CommitPack against other natural and synthetic code instructions (xP3x, Self-Instruct, OASST) on the 16B parameter StarCoder model, and achieve state-of-the-art performance among models not trained on OpenAI outputs, on the HumanEval Python benchmark (46. 2% pass@1).
Ranked #5 on
Code Generation
on HumanEval
Source Code Data Augmentation for Deep Learning: A Survey
This paper fills this gap by conducting a comprehensive and integrative survey of data augmentation for source code, wherein we systematically compile and encapsulate existing literature to provide a comprehensive overview of the field.
FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing
Textual scene graph parsing has become increasingly important in various vision-language applications, including image caption evaluation and image retrieval.
Ranked #2 on
Human Judgment Correlation
on Flickr8k-Expert
DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text
One is called DetectLLM-LRR, which is fast and efficient, and the other is called DetectLLM-NPR, which is more accurate, but slower due to the need for perturbations.
StarCoder: may the source be with you!
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15. 5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention.
Ranked #43 on
Code Generation
on MBPP
ICE-Score: Instructing Large Language Models to Evaluate Code
Token-matching-based metrics, such as BLEU, have demonstrated weak correlations with human practitioners in code intelligence tasks.
Training-free Lexical Backdoor Attacks on Language Models
In this work, we propose Training-Free Lexical Backdoor Attack (TFLexAttack) as the first training-free backdoor attack on language models.
Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity
We believe that our findings may give light on future efforts to determine and mitigate the ethical hazards posed by machines in LLM applications.
On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex
Semantic parsing is a technique aimed at constructing a structured representation of the meaning of a natural-language question.
SantaCoder: don't reach for the stars!
The BigCode project is an open-scientific collaboration working on the responsible development of large language models for code.
ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities
We introduce ViLPAct, a novel vision-language benchmark for human activity planning.
Rethinking Round-Trip Translation for Machine Translation Evaluation
Round-trip translation could be served as a clever and straightforward technique to alleviate the requirement of the parallel evaluation corpus.
Paraphrasing Techniques for Maritime QA system
In this paper, we investigate how to exploit paraphrasing methods for the automated generation of large-scale training datasets (in the form of paraphrased utterances and their corresponding logical forms in SQL format) and present our experimental results using real-world data in the maritime domain.
