Search Results for author:
Found 16 papers, 8 papers with code
ART: Automatic multi-step reasoning and tool-use for large language models
We introduce Automatic Reasoning and Tool-use (ART), a framework that uses frozen LLMs to automatically generate intermediate reasoning steps as a program.
ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices
Such applications demand prediction models with small storage and computational complexity that do not compromise significantly on accuracy.
SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations
We present a feature vector formation technique for documents - Sparse Composite Document Vector (SCDV) - which overcomes several shortcomings of the current distributional paragraph vector representations that are widely used for text representation.
An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
Decisions of complex language understanding models can be rationalized by limiting their inputs to a relevant subsequence of the original text.
PuMer: Pruning and Merging Tokens for Efficient Vision Language Models
Large-scale vision language (VL) models use Transformers to perform cross-modal interactions between the input text and image.
CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation
We present COunterfactual Generation via Retrieval and Editing (CORE), a retrieval-augmented generation framework for creating diverse counterfactual perturbations for CDA.
Entity Projection via Machine Translation for Cross-Lingual NER
Although over 100 languages are supported by strong off-the-shelf machine translation systems, only a subset of them possess large annotated corpora for named entity recognition.
Ranked #4 on
Cross-Lingual NER
on CoNLL 2003
Weighted Global Normalization for Multiple Choice Reading Comprehension over Long Documents
Motivated by recent evidence pointing out the fragility of high-performing span prediction models, we direct our attention to multiple choice reading comprehension.
Contextualized Representations for Low-resource Utterance Tagging
Utterance-level analysis of the speaker{'}s intentions and emotions is a core task in conversational understanding.
FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation
Natural language (NL) explanations of model predictions are gaining popularity as a means to understand and verify decisions made by large black-box pre-trained models, for NLP tasks such as Question Answering (QA) and Fact Verification.
EASE: Extractive-Abstractive Summarization with Explanations
Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability.
Prompting Contrastive Explanations for Commonsense Reasoning Tasks
Many commonsense reasoning NLP tasks involve choosing between one or more possible answers to a question or prompt based on knowledge that is often implicit.
Retrieval-guided Counterfactual Generation for QA
To address these challenges, we develop a Retrieve-Generate-Filter(RGF) technique to create counterfactual evaluation and training data with minimal human supervision.
EASE: Extractive-Abstractive Summarization End-to-End using the Information Bottleneck Principle
To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework that generates concise abstractive summaries that can be traced back to an extractive summary.
AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization
We propose AGRO -- Adversarial Group discovery for Distributionally Robust Optimization -- an end-to-end approach that jointly identifies error-prone groups and improves accuracy on them.
Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals
Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the input (e. g., the hypothesis in NLI) and the label; consequently, models trained only on those outperform chance.
