SACHIN KUMARMemoRAG : dual-stage RAG framework using Memory LLM Model to generate answer clues for relevant…Existing RAG methods constrained inherently, as they can only perform relevance matching between explicitly stated queries and well-formed…7h ago7h ago
SACHIN KUMARReinforcement Learning from Prediction Feedback : LLM fine-tuning method to generate user…LLM-powered personalization agent systems use LLMs to predict users’ behavior from their past activities, with effectiveness hinging on…1d ago1d ago
SACHIN KUMARDebate on Graph: framework leveraging LLMs to debate and reason over knowledge graphsKnowledge Graph Question Answering (KGQA) requires LLMs to answer natural language questions by retrieving relevant triples from knowledge…4d ago4d ago
SACHIN KUMARLongCite: training LLM models to generate fine-grained citations in Long-Context Question AnsweringLack of citations in LLM responses makes user verification difficult, leading to concerns about their trustworthiness due to their…5d ago5d ago
SACHIN KUMARMemLong: Memory-Augmented Retrieval for Long Text LLM GenerationIn this paper[1], authors introduce MemLong: Memory-Augmented Retrieval for Long Text Generation (MemLong, a method designed to enhance the…Sep 2Sep 2
SACHIN KUMARReasoning-Aware Self-Consistency : Leveraging Reasoning Paths for Efficient LLM generation SamplingSelf-Consistency(SC) is widely used method to mitigate hallucinations by sampling the LLM multiple times and outputting the most frequent…Sep 2Sep 2
SACHIN KUMARSIaM: Self-Improving Code-Assisted Mathematical Reasoning of LLMsPotential of improving LLMs by leveraging large-scale,expert-written, diverse math question-answer pairs remains unexplored. To utilize…Sep 2Sep 2
SACHIN KUMARCreating Dynamic Mindmap of information from collaborative discourse among LLM Agents with…LLM powered chatbots and generative search engines excel at answering concrete queries, discovering information in the terrain of unknown…Aug 28Aug 28
SACHIN KUMARMegaAgent: framework for autonomous cooperation in Large-Scale LLM Agent SystemsLLM powered multiagent(LLM-MA) systems mostly follow predefined Standard Operating Procedures(SOPs) that remain unchanged across the whole…Aug 22Aug 22
SACHIN KUMARRAGLAB: Modular and Research-Oriented Unified Framework for Retrieval-Augmented GenerationIn this paper[1], authors introduce RAGLAB, a modular and research-oriented open-source library. RAGLAB reproduces 6 existing algorithms…Aug 22Aug 22