Search Results - "Rajani, Nazneen"

Systematic analysis of 32,111 AI model cards characterizes documentation practice in AI by Liang, Weixin, Rajani, Nazneen, Yang, Xinyu, Ozoani, Ezinwanne, Wu, Eric, Chen, Yiqun, Smith, Daniel Scott, Zou, James

“…The rapid proliferation of AI models has underscored the importance of thorough documentation, which enables users to understand, trust and effectively use…”
Get full text

Explainable Improved Ensembling for Natural Language and Vision by Rajani, Nazneen Fatema

“…Ensemble methods are well-known in machine learning for improving prediction accuracy. However, they do not adequately discriminate among underlying component…”
Get full text

iSEA: An Interactive Pipeline for Semantic Error Analysis of NLP Models by Yuan, Jun, Vig, Jesse, Rajani, Nazneen

“…Error analysis in NLP models is essential to successful model development and deployment. One common approach for diagnosing errors is to identify…”
Get full text

P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts by Newman, Benjamin, Choubey, Prafulla Kumar, Rajani, Nazneen

“…Recent work (e.g. LAMA (Petroni et al., 2019)) has found that the quality of the factual information extracted from Large Language Models (LLMs) depends on the…”
Get full text

VERITAS: A Unified Approach to Reliability Evaluation by Ramamurthy, Rajkumar, Rajeev, Meghana Arakkal, Molenschot, Oliver, Zou, James, Rajani, Nazneen

“…Large language models (LLMs) often fail to synthesize information from their context to generate an accurate response. This renders them unreliable in…”
Get full text

Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations by Saha, Swarnadeep, Hase, Peter, Rajani, Nazneen, Bansal, Mohit

“…Recent work on explainable NLP has shown that few-shot prompting can enable large pretrained language models (LLMs) to generate grammatical and factual natural…”
Get full text

SEAL : Interactive Tool for Systematic Error Analysis and Labeling by Rajani, Nazneen, Liang, Weixin, Chen, Lingjiao, Mitchell, Meg, Zou, James

“…With the advent of Transformers, large language models (LLMs) have saturated well-known NLP benchmarks and leaderboards with high aggregate performance…”
Get full text

Interactive Model Cards: A Human-Centered Approach to Model Documentation by Crisan, Anamaria, Drouhard, Margaret, Vig, Jesse, Rajani, Nazneen

“…Deep learning models for natural language processing (NLP) are increasingly adopted and deployed by analysts without formal training in NLP or machine learning…”
Get full text

HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models by Goyal, Tanya, Rajani, Nazneen Fatema, Liu, Wenhao, Kryściński, Wojciech

“…Summarization systems make numerous "decisions" about summary properties during inference, e.g. degree of copying, specificity and length of outputs, etc…”
Get full text

What's documented in AI? Systematic Analysis of 32K AI Model Cards by Liang, Weixin, Rajani, Nazneen, Yang, Xinyu, Ozoani, Ezinwanne, Wu, Eric, Chen, Yiqun, Smith, Daniel Scott, Zou, James

“…The rapid proliferation of AI models has underscored the importance of thorough documentation, as it enables users to understand, trust, and effectively…”
Get full text

BookSum: A Collection of Datasets for Long-form Narrative Summarization by Kryściński, Wojciech, Rajani, Nazneen, Agarwal, Divyansh, Xiong, Caiming, Radev, Dragomir

“…The majority of available text summarization datasets include short-form source documents that lack long-range causal and temporal dependencies, and often…”
Get full text

Stage-wise Fine-tuning for Graph-to-Text Generation by Wang, Qingyun, Yavuz, Semih, Lin, Victoria, Ji, Heng, Rajani, Nazneen

“…Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they…”
Get full text

SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization by Vig, Jesse, Kryściński, Wojciech, Goel, Karan, Rajani, Nazneen Fatema

“…Novel neural architectures, training strategies, and the availability of large-scale corpora haven been the driving force behind recent progress in abstractive…”
Get full text

Self-rationalization improves LLM as a fine-grained judge by Trivedi, Prapti, Gulati, Aditya, Molenschot, Oliver, Rajeev, Meghana Arakkal, Ramamurthy, Rajkumar, Stevens, Keith, Chaudhery, Tanveesh Singh, Jambholkar, Jahnavi, Zou, James, Rajani, Nazneen

“…LLM-as-a-judge models have been used for evaluating both human and AI generated content, specifically by providing scores and rationales. Rationales, in…”
Get full text

Conformal Predictor for Improving Zero-shot Text Classification Efficiency by Choubey, Prafulla Kumar, Bai, Yu, Wu, Chien-Sheng, Liu, Wenhao, Rajani, Nazneen

“…Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification. 0shot models based on natural language inference (NLI)…”
Get full text

CTRLsum: Towards Generic Controllable Text Summarization by He, Junxian, Kryściński, Wojciech, McCann, Bryan, Rajani, Nazneen, Xiong, Caiming

“…Current summarization systems yield generic summaries that are disconnected from users' preferences and expectations. To address this limitation, we present…”
Get full text

Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models by Sturmfels, Pascal, Vig, Jesse, Madani, Ali, Rajani, Nazneen Fatema

“…For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning…”
Get full text

What's New? Summarizing Contributions in Scientific Literature by Hayashi, Hiroaki, Kryściński, Wojciech, McCann, Bryan, Rajani, Nazneen, Xiong, Caiming

“…With thousands of academic articles shared on a daily basis, it has become increasingly difficult to keep up with the latest scientific findings. To overcome…”
Get full text

Explaining Creative Artifacts by Varshney, Lav R, Rajani, Nazneen Fatema, Socher, Richard

“…Human creativity is often described as the mental process of combining associative elements into a new form, but emerging computational creativity algorithms…”
Get full text

CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization by Choubey, Prafulla Kumar, Fabbri, Alexander R, Vig, Jesse, Wu, Chien-Sheng, Liu, Wenhao, Rajani, Nazneen Fatema

“…Hallucination is a known issue for neural abstractive summarization models. Recent work suggests that the degree of hallucination may depend on errors in the…”
Get full text