Buchumschlag

SafeChat: A Framework for Building Trustworthy Collaborative Assistants and a Case Study of its Usefulness

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Srivastava, Biplav, Lakkaraju, Kausik, Gupta, Nitin, Nagpal, Vansh, Muppasani, Bharath C., Jones, Sara E.
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

BEACON: Balancing Convenience and Nutrition in Meals With Long-Term Group Recommendations and Reasoning on Multimodal Recipes
von: Nagpal, Vansh, et al.
Veröffentlicht: (2024)

GAICo: A Deployed and Extensible Framework for Evaluating Diverse and Multimodal Generative AI Outputs
von: Gupta, Nitin, et al.
Veröffentlicht: (2025)

A Novel Approach to Balance Convenience and Nutrition in Meals With Long-Term Group Recommendations and Reasoning on Multimodal Recipes and its Implementation in BEACON
von: Nagpal, Vansh, et al.
Veröffentlicht: (2024)

The Effect of Human v/s Synthetic Test Data and Round-tripping on Assessment of Sentiment Analysis Systems for Bias
von: Lakkaraju, Kausik, et al.
Veröffentlicht: (2024)

Towards Information-Optimized Multi-Agent Path Finding: A Hybrid Framework with Reduced Inter-Agent Information Sharing
von: Muppasani, Bharath, et al.
Veröffentlicht: (2025)

PLANTS: A Novel Problem and Dataset for Summarization of Planning-Like (PL) Tasks
von: Pallagani, Vishal, et al.
Veröffentlicht: (2024)

Holistic Explainable AI (H-XAI): Extending Transparency Beyond Developers in AI-Driven Decision Making
von: Lakkaraju, Kausik, et al.
Veröffentlicht: (2025)

On Identifying Why and When Foundation Models Perform Well on Time-Series Forecasting Using Automated Explanations and Rating
von: Widener, Michael, et al.
Veröffentlicht: (2025)

Towards Effective Planning Strategies for Dynamic Opinion Networks
von: Muppasani, Bharath, et al.
Veröffentlicht: (2024)

A Planning Ontology to Represent and Exploit Planning Knowledge for Performance Efficiency
von: Muppasani, Bharath, et al.
Veröffentlicht: (2023)

Rating Multi-Modal Time-Series Forecasting Models (MM-TSFM) for Robustness Through a Causal Lens
von: Lakkaraju, Kausik, et al.
Veröffentlicht: (2024)

FABLE: A Novel Data-Flow Analysis Benchmark on Procedural Text for Large Language Model Evaluation
von: Pallagani, Vishal, et al.
Veröffentlicht: (2025)

More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness
von: Li, Aaron J., et al.
Veröffentlicht: (2024)

From Automation to Collaboration: Human-in-the-Loop Methods for Safe and Trustworthy NLP
von: Samu, Most. Sharmin Sultana, et al.
Veröffentlicht: (2026)

Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants
von: Suh, Joseph, et al.
Veröffentlicht: (2026)

Multi-Modal Explainable Medical AI Assistant for Trustworthy Human-AI Collaboration
von: Yang, Honglong, et al.
Veröffentlicht: (2025)

A Neurosymbolic Fast and Slow Architecture for Graph Coloring
von: Khandelwal, Vedant, et al.
Veröffentlicht: (2024)

On Sample-Efficient Generalized Planning via Learned Transition Models
von: Gupta, Nitin, et al.
Veröffentlicht: (2026)

Improvement in Semantic Address Matching using Natural Language Processing
von: Gupta, Vansh, et al.
Veröffentlicht: (2024)

Creating a Causally Grounded Rating Method for Assessing the Robustness of AI Models for Time-Series Forecasting
von: Lakkaraju, Kausik, et al.
Veröffentlicht: (2025)

The Case for Developing a Foundation Model for Planning-like Tasks from Scratch
von: Srivastava, Biplav, et al.
Veröffentlicht: (2024)

Trust and ethical considerations in a multi-modal, explainable AI-driven chatbot tutoring system: The case of collaboratively solving Rubik's Cube
von: Lakkaraju, Kausik, et al.
Veröffentlicht: (2024)

On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)
von: Pallagani, Vishal, et al.
Veröffentlicht: (2024)

Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations
von: Mao, Manqing, et al.
Veröffentlicht: (2024)

Scaling Efficient LLMs
von: Kausik, B. N.
Veröffentlicht: (2024)

GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant
von: Shen, Zhuokang, et al.
Veröffentlicht: (2026)

Assessing Web Search Credibility and Response Groundedness in Chat Assistants
von: Vykopal, Ivan, et al.
Veröffentlicht: (2025)

Human-AI Collaborative Taxonomy Construction: A Case Study in Profession-Specific Writing Assistants
von: Lee, Minhwa, et al.
Veröffentlicht: (2024)

JT-Safe: Intrinsically Enhancing the Safety and Trustworthiness of LLMs
von: Feng, Junlan, et al.
Veröffentlicht: (2025)

A Study on Effect of Reference Knowledge Choice in Generating Technical Content Relevant to SAPPhIRE Model Using Large Language Model
von: Bhattacharya, Kausik, et al.
Veröffentlicht: (2024)

An EcoSage Assistant: Towards Building A Multimodal Plant Care Dialogue Assistant
von: Tomar, Mohit, et al.
Veröffentlicht: (2024)

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
von: Wu, Di, et al.
Veröffentlicht: (2024)

Do Voters Get the Information They Want? Understanding Authentic Voter FAQs in the US and How to Improve for Informed Electoral Participation
von: Rawte, Vipula, et al.
Veröffentlicht: (2024)

A Case Study on the Effectiveness of LLMs in Verification with Proof Assistants
von: Bayazıt, Barış, et al.
Veröffentlicht: (2025)

Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS'24 Experiment
von: Goldberg, Alexander, et al.
Veröffentlicht: (2024)

Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols
von: Hu, Julia, et al.
Veröffentlicht: (2026)

Advancing SLM Tool-Use Capability using Reinforcement Learning
von: Paprunia, Dhruvi, et al.
Veröffentlicht: (2025)

Building A Coding Assistant via the Retrieval-Augmented Language Model
von: Li, Xinze, et al.
Veröffentlicht: (2024)

Multilingual Performance Biases of Large Language Models in Education
von: Gupta, Vansh, et al.
Veröffentlicht: (2025)

Jill Watson: A Virtual Teaching Assistant powered by ChatGPT
von: Taneja, Karan, et al.
Veröffentlicht: (2024)