Search Results for author:
Found 29 papers, 13 papers with code
SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories
To advance towards this goal, we introduce SUPER, the first benchmark designed to evaluate the capability of LLMs in setting up and executing tasks from research repositories.
Practical and Robust Safety Guarantees for Advanced Counterfactual Learning to Rank
Our experiments show that both our novel safe doubly robust method and PRPO provide higher performance than the existing safe inverse propensity scoring approach.
AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
To remedy this gap, we built $\textbf{AppWorld Engine}$, a high-quality execution environment (60K lines of code) of 9 day-to-day apps operable via 457 APIs and populated with realistic digital activities simulating the lives of ~100 fictitious users.
Optimal Baseline Corrections for Off-Policy Contextual Bandits
The foundation of our framework is the derivation of an equivalent baseline correction for all of the existing control variates.
A First Look at Selection Bias in Preference Elicitation for Recommendation
Despite the fact that the extreme sparsity of preference elicitation interactions make them severely more prone to selection bias than natural interactions, the effect of selection bias in preference elicitation on the resulting recommendations has not been studied yet.
LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
Mathematical equations have been unreasonably effective in describing complex natural phenomena across various scientific disciplines.
NTIRE 2024 Quality Assessment of AI-Generated Content Challenge
A total of 196 participants have registered in the video track.
Exploring Explainability in Video Action Recognition
To address these, we introduce Video-TCAV, by building on TCAV for Image Classification tasks, which aims to quantify the importance of specific concepts in the decision-making process of Video Action Recognition models.
Comparison of pipeline, sequence-to-sequence, and GPT models for end-to-end relation extraction: experiments with the rare disease use-case
Our contribution is also the first to conduct E2ERE for the RareDis dataset.
Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
Our experiments with ChatGPT-3. 5 show that this bias is ubiquitous - 80% of our personas demonstrate bias; it is significant - some datasets show performance drops of 70%+; and can be especially harmful for certain groups - some personas suffer statistically significant drops on 80%+ of the datasets.
Top K Relevant Passage Retrieval for Biomedical Question Answering
In this work, we work on the existing DPR framework for the biomedical domain and retrieve answers from the Pubmed articles which is a reliable source to answer medical questions.
Recent Advances in the Foundations and Applications of Unbiased Learning to Rank
This tutorial provides both an introduction to the core concepts of the field and an overview of recent advancements in its foundations along with several applications of its methods.
Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization
For the CLTR field, our novel exposure-based risk minimization method enables practitioners to adopt CLTR methods in a safer manner that mitigates many of the risks attached to previous methods.
Self-Refine: Iterative Refinement with Self-Feedback
Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners
Traditional multi-task learning (MTL) methods use dense networks that use the same set of shared weights across several different tasks.
Knowledge Infused Decoding
Hence, they tend to suffer from counterfactual or hallucinatory generation when used in knowledge-intensive natural language generation (NLG) tasks.
Ranked #2 on
Question Answering
on KILT: ELI5
Lung-Originated Tumor Segmentation from Computed Tomography Scan (LOTUS) Benchmark
Lung cancer is one of the deadliest cancers, and in part its effective diagnosis and treatment depend on the accurate delineation of the tumor.
Exploring Low-Cost Transformer Model Compression for Large-Scale Commercial Reply Suggestions
Fine-tuning pre-trained language models improves the quality of commercial reply suggestion systems, but at the cost of unsustainable training times.
Performance of Dense Coding and Teleportation for Random States --Augmentation via Pre-processing
The local pre-processing employed here is based on positive operator valued measurements along with classical communication and we show that unlike dense coding with two-qubit random states, senders' operations are always helpful to probabilistically enhance the capabilities of implementing dense coding as well as teleportation.
Quantum Physics
Feature Extraction Functions for Neural Logic Rule Learning
Combining symbolic human knowledge with neural networks provides a rule-based ante-hoc explanation of the output.
IITK-RSA at SemEval-2020 Task 5: Detecting Counterfactuals
This paper describes our efforts in tackling Task 5 of SemEval-2020.
Genuine Einstein-Podolsky-Rosen steering of three-qubit states by multiple sequential observers
We investigate the possibility of multiple use of a single copy of three-qubit states for genuine tripartite Einstein-Podolsky-Rosen (EPR) steering.
Quantum Physics
On Application of Bayesian Parametric and Non-parametric Methods for User Cohorting in Product Search
To the best of our knowledge, this is the first work that presents a comparative study of various Bayesian clustering methods in the context of product search.
Multi-Task Learning for Extraction of Adverse Drug Reaction Mentions from Tweets
Adverse drug reactions (ADRs) are one of the leading causes of mortality in health care.
Co-training for Extraction of Adverse Drug Reaction Mentions from Tweets
Adverse drug reactions (ADRs) are one of the leading causes of mortality in health care.
Semi-Supervised Recurrent Neural Network for Adverse Drug Reaction Mention Extraction
Current methods in ADR mention extraction relies on supervised learning methods, which suffers from labeled data scarcity problem.
Making Travel Smarter: Extracting Travel Information From Email Itineraries Using Named Entity Recognition
The purpose of this research is to address the problem of extracting information from travel itineraries and discuss the challenges faced in the process.
Deep Learning for Hate Speech Detection in Tweets
Hate speech detection on Twitter is critical for applications like controversial event extraction, building AI chatterbots, content recommendation, and sentiment analysis.
