SOTAVerified

Chatbot

Chatbot or conversational AI is a language model designed and implemented to have conversations with humans.

Source: Open Data Chatbot

Image source

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 971 papers

TitleStatusHype
Diagnosing Infeasible Optimization Problems Using Large Language ModelsCode1
Domain-specific ChatBots for Science using EmbeddingsCode1
KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue BenchmarkCode1
Knowledge Graph-Driven Retrieval-Augmented Generation: Integrating Deepseek-R1 with Weaviate for Advanced Chatbot ApplicationsCode1
K-PLUG: KNOWLEDGE-INJECTED PRE-TRAINED LANGUAGE MODEL FOR NATURAL LANGUAGE UNDERSTANDING AND GENERATIONCode1
CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract PatientsCode1
Empathy-driven Arabic Conversational ChatbotCode1
Improving Ontology Requirements Engineering with OntoChat and Participatory PromptingCode1
Bring Your Own Data! Self-Supervised Evaluation for Large Language ModelsCode1
Improving Your Model Ranking on Chatbot Arena by Vote RiggingCode1
Hydragen: High-Throughput LLM Inference with Shared PrefixesCode1
Inverse Constitutional AI: Compressing Preferences into PrinciplesCode1
EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability TreesCode1
HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional AttentionCode1
A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWaresCode1
There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal MemoryCode1
Towards a Human-like Open-Domain ChatbotCode1
Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language ModelCode1
Automatic Evaluation and Moderation of Open-domain Dialogue SystemsCode1
Align on the Fly: Adapting Chatbot Behavior to Established NormsCode1
BioImage.IO Chatbot: A Community-Driven AI Assistant for Integrative Computational BioimagingCode1
Visual DialogCode1
How Robust is Google's Bard to Adversarial Image Attacks?Code1
Few Shot Dialogue State Tracking using Meta-learningCode1
FinChat: Corpus and evaluation setup for Finnish chat conversations on everyday topicsCode0
Show:102550
← PrevPage 5 of 39Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Yi 34B ChatAverage win rate27.2—Unverified