Search Results for author:
Found 14 papers, 12 papers with code
Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection
Advanced large language models (LLMs) can generate text almost indistinguishable from human-written text, highlighting the importance of LLM-generated text detection.
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.
NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens
The rapid advancement of Large Language Models (LLMs) has introduced a new frontier in natural language processing, particularly in understanding and processing long-context information.
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).
Supervised Knowledge Makes Large Language Models Better In-context Learners
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering.
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.
Non-Autoregressive Document-Level Machine Translation
However, current NAT models still have a significant performance gap compared to their AT counterparts.
Target-Side Augmentation for Document-Level Machine Translation
Document-level machine translation faces the challenge of data sparsity due to its long input length and a small amount of training data, increasing the risk of learning spurious patterns.
Token-Level Fitting Issues of Seq2seq Models
Sequence-to-sequence (seq2seq) models have been widely used for natural language processing, computer vision, and other deep learning tasks.
GEMINI: Controlling the Sentence-level Writing Style for Abstractive Text Summarization
To address this issue, we propose an adaptive model, GEMINI, that integrates a rewriter and a generator to mimic the sentence rewriting and abstracting techniques, respectively.
A General Contextualized Rewriting Framework for Text Summarization
The rewriting method for text summarization combines extractive and abstractive approaches, improving the conciseness and readability of extractive summaries using an abstractive model.
G-Transformer for Document-level Machine Translation
However, study shows that when we further enlarge the translation unit to a whole document, supervised training of Transformer can fail.
Contextualized Rewriting for Text Summarization
Extractive summarization suffers from irrelevance, redundancy and incoherence.
What Have We Achieved on Text Summarization?
Deep learning has led to significant improvement in text summarization with various methods investigated and improved ROUGE scores reported over the years.
