Search Results for author:
Found 36 papers, 2 papers with code
Navigating Semantic Relations: Challenges for Language Models in Abstract Common-Sense Reasoning
Large language models (LLMs) have achieved remarkable performance in generating human-like text and solving reasoning tasks of moderate complexity, such as question-answering and mathematical problem-solving.
Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models
Research on emergent patterns in Large Language Models (LLMs) has gained significant traction in both psychology and artificial intelligence, motivating the need for a comprehensive review that offers a synthesis of this complex landscape.
SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL
In recent years, Text-to-SQL, the problem of automatically converting questions posed in natural language to formal SQL queries, has emerged as an important problem at the intersection of natural language processing and data management research.
Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference
One such set of risks arises from misplaced confidence, whether over-confidence or under-confidence, that the models have in their inference.
GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning
Spatial reasoning, an important faculty of human cognition with many practical applications, is one of the core commonsense skills that is not purely language-based and, for satisfying (as opposed to optimal) solutions, requires some minimum degree of planning.
Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions
Personality, a fundamental aspect of human cognition, contains a range of traits that influence behaviors, thoughts, and emotions.
An Evaluation of Estimative Uncertainty in Large Language Models
Words of estimative probability (WEPs), such as ''maybe'' or ''probably not'' are ubiquitous in natural language for communicating estimative uncertainty, compared with direct statements involving numerical probability.
HALO: An Ontology for Representing and Categorizing Hallucinations in Large Language Models
Recent progress in generative AI, including large language models (LLMs) like ChatGPT, has opened up significant opportunities in fields ranging from natural language processing to knowledge discovery and data mining.
Cost-Efficient Prompt Engineering for Unsupervised Entity Resolution
We use an extensive set of experimental results to show that an LLM like GPT3. 5 is viable for high-performing unsupervised ER, and interestingly, that more complicated and detailed (and hence, expensive) prompting methods do not necessarily outperform simpler approaches.
A Knowledge Graph-Based Search Engine for Robustly Finding Doctors and Locations in the Healthcare Domain
Efficiently finding doctors and locations is an important search problem for patients in the healthcare domain, for which traditional information retrieval methods tend not to work optimally.
A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores
We also propose a risk-centric evaluation framework, and four novel metrics, for assessing LLMs on these risks in both in-domain and out-of-domain settings.
Named Entity Resolution in Personal Knowledge Graphs
We begin with a formal definition of the problem, and the components necessary for doing high-quality and efficient ER.
Toward Defining a Domain Complexity Measure Across Domains
The extrinsic domain complexity is agent- and task-dependent.
A Pilot Evaluation of ChatGPT and DALL-E 2 on Decision Making and Spatial Reasoning
We conduct a pilot study selectively evaluating the cognitive abilities (decision making and spatial reasoning) of two recently released generative transformer models, ChatGPT and DALL-E 2.
On the Empirical Association between Trade Network Complexity and Global Gross Domestic Product
In recent decades, trade between nations has constituted an important component of global Gross Domestic Product (GDP), with official estimates showing that it likely accounted for a quarter of total global production.
Can Language Representation Models Think in Bets?
Through a robust body of experiments on four established LRMs, we show that a model is only able to `think in bets' if it is first fine-tuned on bet questions with an identical structure.
Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes
Recent work on transformer-based neural networks has led to impressive advances on multiple-choice natural language understanding (NLU) problems, such as Question Answering (QA) and abductive reasoning.
Understanding Substructures in Commonsense Relations in ConceptNet
A potential source of structured commonsense knowledge that could be used to derive insights is ConceptNet.
A Theoretically Grounded Benchmark for Evaluating Machine Commonsense
Preliminary results suggest that the benchmark is challenging even for advanced language representation models designed for discriminative CSR question answering tasks.
Understanding COVID-19 Vaccine Reaction through Comparative Analysis on Twitter
Although multiple COVID-19 vaccines have been available for several months now, vaccine hesitancy continues to be at high levels in the United States.
Predicting Zip Code-Level Vaccine Hesitancy in US Metropolitan Areas Using Machine Learning Models on Public Tweets
At the same time, the advent of social media suggests that it may be possible to get vaccine hesitancy signals at an aggregate level (such as at the level of zip codes) by using machine learning models and socioeconomic (and other) features from publicly available sources.
Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach
Monopoly is a popular strategic board game that requires players to make multiple decisions during the game.
A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
Acquiring commonsense knowledge and reasoning is recognized as an important frontier in achieving general Artificial Intelligence (AI).
Do Fine-tuned Commonsense Language Models Really Generalize?
According to influential leaderboards hosted by the Allen Institute (evaluating state-of-the-art performance on commonsense reasoning benchmarks), models based on such transformer methods are approaching human-like performance and have average accuracy well over 80% on many benchmarks.
On using Product-Specific Schema.org from Web Data Commons: An Empirical Set of Best Practices
Rather than simple analysis, the goal of our study is to devise an empirically grounded set of best practices for using and consuming WDC product-specific schema. org data.
An Experimental Study of The Effects of Position Bias on Emotion CauseExtraction
We therefore conclude that it is the innate bias in this benchmark that caused high accuracy rate of these deep learning models in ECE.
Low-supervision urgency detection and transfer in short crisis messages
Humanitarian disasters have been on the rise in recent years due to the effects of climate change and socio-political situations such as the refugee crisis.
FlagIt: A System for Minimally Supervised Human Trafficking Indicator Mining
In this paper, we describe and study the indicator mining problem in the online sex advertising domain.
Always Lurking: Understanding and Mitigating Bias in Online Human Trafficking Detection
Web-based human trafficking activity has increased in recent years but it remains sparsely dispersed among escort advertisements and difficult to identify due to its often-latent nature.
Predicting Role Relevance with Minimal Domain Expertise in a Financial Domain
Word embeddings have made enormous inroads in recent years in a wide variety of text mining applications.
Using Contexts and Constraints for Improved Geotagging of Human Trafficking Webpages
Extracting geographical tags from webpages is a well-motivated application in many domains.
Supervised Typing of Big Graphs using Semantic Embeddings
We propose a supervised algorithm for generating type embeddings in the same semantic vector space as a given set of entity embeddings.
Information Extraction in Illicit Domains
Extracting useful entities and attribute values from illicit domains such as human trafficking is a challenging problem with the potential for widespread social impact.
An Ensemble Blocking Scheme for Entity Resolution of Large and Sparse Datasets
Entity Resolution, also called record linkage or deduplication, refers to the process of identifying and merging duplicate versions of the same entity into a unified representation.
Adaptive Candidate Generation for Scalable Edge-discovery Tasks on Data Graphs
With such a development, the complexity-reducing scope of DNF schemes becomes applicable to a variety of problems, including entity resolution and type alignment between heterogeneous graphs, and link prediction in networks represented as attributed graphs.
