244 citations · 446 across the 35 of their papers we have counts for
36 papers
Lost in Literalism: How Supervised Training Shapes Translationese in LLMs
Yafu Li, Ronghao Zhang, Zhilin Wang +5
Large language models (LLMs) have achieved remarkable success in machine translation, demonstrating impressive performance across diverse languages. However, translationese, charac…
ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
Shulin Huang, Linyi Yang, Yan Song +9
Evaluating large language models (LLMs) poses significant challenges, particularly due to issues of data contamination and the leakage of correct answers. To address these challeng…
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Yu Zhang, Songlin Yang, Ruijie Zhu +9
Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks comp…
Alleviating Hallucinations of Large Language Models through Induced Hallucinations
Yue Zhang, Leyang Cui, Wei Bi +1
Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonl…
Non-autoregressive Text Editing with Copy-aware Latent Alignments
Yu Zhang, Yue Zhang, Leyang Cui +1
Recent work has witnessed a paradigm shift from Seq2Seq to Seq2Edit in the field of text editing, with the aim of addressing the slow autoregressive inference problem posed by the…
RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation
Yue Zhang, Leyang Cui, Enbo Zhao +2
Grammatical Error Correction (GEC) systems play a vital role in assisting people with their daily writing tasks. However, users may sometimes come across a GEC system that initiall…
Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks
Qintong Li, Leyang Cui, Lingpeng Kong +1
Previous work adopts large language models (LLMs) as evaluators to evaluate natural language process (NLP) tasks. However, certain shortcomings, e.g., fairness, scope, and accuracy…
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Yue Zhang, Yafu Li, Leyang Cui +13
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit h…
Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling
Longyue Wang, Zefeng Du, Donghuai Liu +7
Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP). However, existing…
Automated Action Model Acquisition from Narrative Texts
Ruiqi Li, Leyang Cui, Songtuan Lin +1
Action models, which take the form of precondition/effect axioms, facilitate causal and motivational connections between actions for AI agents. Action model acquisition has been id…
Explicit Syntactic Guidance for Neural Text Generation
Yafu Li, Leyang Cui, Jianhao Yan +4
Most existing text generation models follow the sequence-to-sequence paradigm. Generative Grammar suggests that humans generate natural language texts by learning language grammar.…
Enhancing Grammatical Error Correction Systems with Explanations
Yuejiao Fei, Leyang Cui, Sen Yang +3
Grammatical error correction systems improve written communication by detecting and correcting language mistakes. To help language learners better understand why the GEC system mak…
Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance
Yue Zhang, Leyang Cui, Deng Cai +3
Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks. Recent st…
LogiCoT: Logical Chain-of-Thought Instruction-Tuning
Hanmeng Liu, Zhiyang Teng, Leyang Cui +3
Generative Pre-trained Transformer 4 (GPT-4) demonstrates impressive chain-of-thought reasoning ability. Recent work on self-instruction tuning, such as Alpaca, has focused on enha…
EDeR: A Dataset for Exploring Dependency Relations Between Events
Ruiqi Li, Patrik Haslum, Leyang Cui
Relation extraction is a central task in natural language processing (NLP) and information retrieval (IR) research. We argue that an important type of relation not explored in NLP…
Cross-domain Generalization for AMR Parsing
Xuefeng Bai, Seng Yang, Leyang Cui +2
Abstract Meaning Representation (AMR) parsing aims to predict an AMR graph from textual input. Recently, there has been notable growth in AMR parsing performance. However, most exi…
Multi-Granularity Optimization for Non-Autoregressive Translation
Yafu Li, Leyang Cui, Yongjing Yin +1
Despite low latency, non-autoregressive machine translation (NAT) suffers severe performance deterioration due to the naive independence assumption. This assumption is further stre…
Effidit: Your AI Writing Assistant
Shuming Shi, Enbo Zhao, Duyu Tang +10
In this technical report, we introduce Effidit (Efficient and Intelligent Editing), a digital writing assistant that facilitates users to write higher-quality text more efficiently…
FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition
Linyi Yang, Lifan Yuan, Leyang Cui +2
Few-shot Named Entity Recognition (NER) is imperative for entity tagging in limited resource domains and thus received proper attention in recent years. Existing approaches for few…
Towards Robust Online Dialogue Response Generation
Leyang Cui, Fandong Meng, Yijin Liu +2
Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-w…
Do Prompts Solve NLP Tasks Using Natural Language?
Sen Yang, Yunchen Zhang, Leyang Cui +1
Thanks to the advanced improvement of large pre-trained language models, prompt-based fine-tuning is shown to be effective on a variety of downstream tasks. Though many prompting m…
Solving Aspect Category Sentiment Analysis as a Text Generation Task
Jian Liu, Zhiyang Teng, Leyang Cui +2
Aspect category sentiment analysis has attracted increasing research attention. The dominant methods make use of pre-trained language models by learning effective aspect category-s…
Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation
Leyang Cui, Yu Wu, Shujie Liu +1
Although pre-training models have achieved great success in dialogue generation, their performance drops dramatically when the input contains an entity that does not appear in pre-…
Investigating Non-local Features for Neural Constituency Parsing
Leyang Cui, Sen Yang, Yue Zhang
Thanks to the strong representation power of neural encoders, neural chart-based parsers have achieved highly competitive performance by using local features. Recently, it has been…