SOTAVerified

Response Generation

A task where an agent should play the $DE$ role and generate a text to respond to a $P$ message.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 914 papers

TitleStatusHype
Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria RerankingCode13
Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language ModelsCode11
Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented GenerationCode4
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionCode4
Guiding Instruction-based Image Editing via Multimodal Large Language ModelsCode4
Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in ChineseCode4
Tool Learning with Large Language Models: A SurveyCode3
From Matching to Generation: A Survey on Generative Information RetrievalCode3
NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference ChecklistCode3
Self-Refine: Iterative Refinement with Self-FeedbackCode3
Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education SystemsCode2
VideoRAG: Retrieval-Augmented Generation over Video CorpusCode2
Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local AttentionCode2
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation GenerationCode2
Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function OptimizationCode2
Fact Finder -- Enhancing Domain Expertise of Large Language Models by Incorporating Knowledge GraphsCode2
AGLA: Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local AttentionCode2
ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPOCode2
Hello Again! LLM-powered Personalized Agent for Long-term DialogueCode2
CtrlA: Adaptive Retrieval-Augmented Generation via Inherent ControlCode2
Large Language Models as Zero-shot Dialogue State Tracker through Function CallingCode2
CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular FusionCode2
STICKERCONV: Generating Multimodal Empathetic Responses from ScratchCode2
Compressing Context to Enhance Inference Efficiency of Large Language ModelsCode2
SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine CollaborationCode2
On Evaluating Adversarial Robustness of Large Vision-Language ModelsCode2
Towards a Unified Multi-Dimensional Evaluator for Text GenerationCode2
DIALOGPT : Large-Scale Generative Pre-training for Conversational Response GenerationCode2
MASS: Masked Sequence to Sequence Pre-training for Language GenerationCode2
Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement LearningCode1
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge GraphsCode1
Neuro-Symbolic Query CompilerCode1
Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object PerceptionCode1
MSCRS: Multi-modal Semantic Graph Prompt Learning Framework for Conversational Recommender SystemsCode1
LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation ConversationCode1
Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language ModelsCode1
Emotional RAG: Enhancing Role-Playing Agents through Emotional RetrievalCode1
Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience ReportCode1
Towards Empathetic Conversational Recommender SystemsCode1
BI-MDRG: Bridging Image History in Multimodal Dialogue Response GenerationCode1
Empathy Level Alignment via Reinforcement Learning for Empathetic Response GenerationCode1
Towards Aligning Language Models with Textual FeedbackCode1
MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical ContextCode1
ESCoT: Towards Interpretable Emotional Support Dialogue SystemsCode1
Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMsCode1
The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)Code1
Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational SearchCode1
ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and PersonalizationCode1
Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting TranscriptsCode1
Aligning LLM Agents by Learning Latent Preference from User EditsCode1
Show:102550
← PrevPage 1 of 19Next →
All datasetsSIMMC2.0ArgSciChatMMConv

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PaCEBLEU34.1—Unverified
2BART-largeBLEU33.1—Unverified
3BART-baseBLEU29.4—Unverified
4MTNBLEU21.7—Unverified
5GPT-2BLEU19.2—Unverified
#ModelMetricClaimedVerifiedStatus
1LED(Q,F)Message-F119.54—Unverified
2LED(Q,P,H)Message-F116.14—Unverified
3LED(Q,P)Message-F114.25—Unverified
#ModelMetricClaimedVerifiedStatus
1PaCEBLEU22—Unverified
2SimpleTODBLEU20.3—Unverified