Search Results for author:
Found 29 papers, 11 papers with code
POSIX: A Prompt Sensitivity Index For Large Language Models
Despite their remarkable capabilities, Large Language Models (LLMs) are found to be surprisingly sensitive to minor variations in prompts, often generating significantly divergent outputs in response to minor variations in the prompts, such as spelling errors, alteration of wording or the prompt template.
Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models
Existing debiasing techniques are typically training-based or require access to the model's internals and output distributions, so they are inaccessible to end-users looking to adapt LLM outputs for their particular needs.
xLP: Explainable Link Prediction for Master Data Management
Explaining neural model predictions to users requires creativity.
SMART: Submodular Data Mixture Strategy for Instruction Tuning
Instruction Tuning involves finetuning a language model on a collection of instruction-formatted datasets in order to enhance the generalizability of the model to unseen tasks.
CABINET: Content Relevance based Noise Reduction for Table Question Answering
Typically, only a small part of the whole table is relevant to derive the answer for a given question.
Ranked #1 on
Semantic Parsing
on WikiSQL
(Denotation accuracy (test) metric)
All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation
Fairness in Language Models (LMs) remains a longstanding challenge, given the inherent biases in training data that can be perpetuated by models and affect the downstream tasks.
Neuro-Symbolic RDF and Description Logic Reasoners: The State-Of-The-Art and Challenges
Ontologies are used in various domains, with RDF and OWL being prominent standards for ontology development.
Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems
To this end, we propose UNIT, a UNified dIalogue dataseT constructed from conversations of existing datasets for different dialogue tasks capturing the nuances for each of them.
HyHTM: Hyperbolic Geometry based Hierarchical Topic Models
We present HyHTM - a Hyperbolic geometry based Hierarchical Topic Models - that addresses these limitations by incorporating hierarchical information from hyperbolic geometry to explicitly model hierarchies in topic models.
INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models
A salient characteristic of pre-trained language models (PTLMs) is a remarkable improvement in their generalization capability and emergence of new capabilities with increasing model capacity and pre-training dataset size.
Explain like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation
Neural retrieval models (NRMs) have been shown to outperform their statistical counterparts owing to their ability to capture semantic meaning via dense document representations.
Expressive Reasoning Graph Store: A Unified Framework for Managing RDF and Property Graph Databases
Resource Description Framework (RDF) and Property Graph (PG) are the two most commonly used data models for representing, storing, and querying graph data.
LM-CORE: Language Models with Contextually Relevant External Knowledge
Large transformer-based pre-trained language models have achieved impressive performance on a variety of knowledge-intensive tasks and can capture factual knowledge in their parameters.
CoSe-Co: Text Conditioned Generative CommonSense Contextualizer
To train CoSe-Co, we propose a novel dataset comprising of sentence and commonsense knowledge pairs.
CyCLIP: Cyclic Contrastive Language-Image Pretraining
Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness.
Why Did You Not Compare With That? Identifying Papers for Use as Baselines
We frame the problem as a binary classification task where all the references in a paper are to be classified as either baselines or non-baselines.
SERC: Syntactic and Semantic Sequence based Event Relation Classification
We propose an LSTM based model for temporal and causal relation classification that captures the interrelations between the three encoded features.
Why Settle for Just One? Extending EL++ Ontology Embeddings with Many-to-Many Relationships
However, most of the existing KG embeddings only consider the network structure of the graph and ignore the semantics and the characteristics of the underlying ontology that provides crucial information about relationships between entities in the KG.
CoSe-Co: Sentence Conditioned Generative CommonSense Contextualizer for Language Models
Pre-trained Language Models (PTLMs) have been shown to perform well on natural language reasoning tasks requiring commonsense.
No Need to Know Everything! Efficiently Augmenting Language Models With External Knowledge
This allows the training of the language model to be de-coupled from the external knowledge source and the latter can be updated without affecting the parameters of the language model.
Schema Aware Semantic Reasoning for Interpreting Natural Language Queries in Enterprise Settings
We posit that deploying ontology reasoning over domain semantics can help in achieving better natural language understanding for QA systems.
ECIR 2020 Workshops: Assessing the Impact of Going Online
In this report, we describe the experience of organizing the ECIR 2020 Workshops in this scenario from two perspectives: the workshop organizers and the workshop participants.
A Topic-Aligned Multilingual Corpus of Wikipedia Articles for Studying Information Asymmetry in Low Resource Languages
Wikipedia is the largest web-based open encyclopedia covering more than three hundred languages.
Link Prediction using Graph Neural Networks for Master Data Management
Learning graph representations of n-ary relational data has a number of real world applications like anti-money laundering, fraud detection, and customer due diligence.
Topic-Specific Sentiment Analysis Can Help Identify Political Ideology
Ideological leanings of an individual can often be gauged by the sentiment one expresses about different issues.
Bernoulli Embeddings for Graphs
Just as semantic hashing can accelerate information retrieval, binary valued embeddings can significantly reduce latency in the retrieval of graphical data.
Tell Me Why Is It So? Explaining Knowledge Graph Relationships by Finding Descriptive Support Passages
We address the problem of finding descriptive explanations of facts stored in a knowledge graph.
