Search Results for author:
Found 16 papers, 6 papers with code
Zero-shot Entity Linking with Less Data
Interestingly, we discovered that BLINK exhibits diminishing returns, i. e., it reaches 98% of its performance with just 1% of the training data and the remaining 99% of the data yields only a marginal increase of 2% in the performance.
CETBench: A Novel Dataset constructed via Transformations over Programs for Benchmarking LLMs for Code-Equivalence Checking
Our analysis on this dataset reveals a surprising finding that very simple code transformations in the underlying pair of programs can result in a significant drop in performance of SOTA LLMs for the task of code-equivalence checking.
Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models
By utilizing the model's correct responses, S3FT reduces model specialization during the fine-tuning stage.
Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG
While RAG enhances response relevance by incorporating retrieved domain knowledge in the context, retrieval errors can still lead to hallucinations and incorrect answers.
Fill in the Blank: Exploring and Enhancing LLM Capabilities for Backward Reasoning in Math Word Problems
Extensive experimentation demonstrates successive improvement in the performance of LLMs on the backward reasoning task, using our strategies, with our ensemble-based method resulting in significant performance gains compared to the SOTA forward reasoning strategies we adapt.
Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach
We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces.
Targeted Extraction of Temporal Facts from Textual Resources for Improved Temporal Question Answering over Knowledge Bases
This allows us to spot those facts that failed to get retrieved from the KB and generate textual queries to extract them from the textual resources in an open-domain question answering fashion.
Knowledge Base Question Answering
Open-Domain Question Answering
+1
A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases
Specifically, our benchmark is a temporal question answering dataset with the following advantages: (a) it is based on Wikidata, which is the most frequently curated, openly available knowledge base, (b) it includes intermediate sparql queries to facilitate the evaluation of semantic parsing based approaches for KBQA, and (c) it generalizes to multiple knowledge bases: Freebase and Wikidata.
SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases
In addition, to demonstrate extensi-bility to additional reasoning types we evaluate on multi-hopreasoning datasets and a new Temporal KBQA benchmarkdataset on Wikidata, namedTempQA-WD1, introduced in thispaper.
Ranked #2 on
Question Answering
on TempQA-WD
Knowledge Graph Question Answering via SPARQL Silhouette Generation
Experimental results show that the quality of generated SPARQL silhouette in the first stage is outstanding for the ideal scenarios but for realistic scenarios (i. e. noisy linker), the quality of the resulting SPARQL silhouette drops drastically.
Explanations for CommonsenseQA: New Dataset and Models
We human-annotate a first-of-its-kind dataset (called ECQA) of positive and negative properties, as well as free-flow explanations, for $11K$ QA pairs taken from the CQA dataset.
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
Knowledge base question answering (KBQA)is an important task in Natural Language Processing.
Inductive Quantum Embedding
Our training runs 9-times faster than the original QE scheme on this task.
The TechQA Dataset
We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain.
A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation
Designing such a network, as well as collecting jointly labeled data for training is a non-trivial task.
Max-Margin Feature Selection
In this paper, we formulate the task of feature selection as a one class SVM problem in a space where features correspond to the data points and instances correspond to the dimensions.
