Search Results for author: Raviteja Anantha

Found 9 papers, 2 papers with code

ProTIP: Progressive Tool Retrieval Improves Planning

no code implementations16 Dec 2023 Raviteja Anantha, Bortik Bandyopadhyay, Anirudh Kashi, Sayantan Mahinder, Andrew W Hill, Srinivas Chappidi

Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes.

Contrastive Learning Retrieval

Context Tuning for Retrieval Augmented Generation

no code implementations9 Dec 2023 Raviteja Anantha, Tharun Bethi, Danil Vodianik, Srinivas Chappidi

To address this limitation, we propose Context Tuning for RAG, which employs a smart context retrieval system to fetch relevant information that improves both tool retrieval and plan generation.

Hallucination Retrieval

Generalized Reinforcement Meta Learning for Few-Shot Optimization

no code implementations4 May 2020 Raviteja Anantha, Stephen Pulman, Srinivas Chappidi

We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning.

Decoder Few-Shot Learning +1

Question Rewriting for Conversational Question Answering

no code implementations30 Apr 2020 Svitlana Vakulenko, Shayne Longpre, Zhucheng Tu, Raviteja Anantha

Conversational question answering (QA) requires the ability to correctly interpret a question in the context of previous conversation turns.

Passage Retrieval Question Rewriting +1

Learning to Rank Intents in Voice Assistants

no code implementations30 Apr 2020 Raviteja Anantha, Srinivas Chappidi, William Dawoodi

Voice Assistants aim to fulfill user requests by choosing the best intent from multiple options generated by its Automated Speech Recognition and Natural Language Understanding sub-systems.

Denoising Learning-To-Rank +3

Cannot find the paper you are looking for? You can Submit a new open access paper.