Praveen ThenrajinResearch Papers SummarizedE25 : Strategic Chain-of-ThoughtIdentifying the correct strategy (a pre and well defined method or step) to solve a problem, helps to generate efficient and stable CoT…Oct 6Oct 6
Praveen ThenrajinResearch Papers SummarizedE26 : ReAct — Synergizing Reasoning and Acting in Language ModelsCombining reasoning along with actioning helps to solve knowledge-intensive reasoning and interactive decision making problems better than…Jun 23Jun 23
Praveen ThenrajinResearch Papers SummarizedE25 : The Unreasonable Ineffectiveness of the Deeper LayersJun 16Jun 16
Praveen ThenrajinResearch Papers SummarizedE24 : Does Fine-tuning LLMs On New Knowledge Encourage Hallucinations?Fine-tuning a LLM using new factual knowledge data degrades the performance of LLM by encouraging them to hallucinateJun 9Jun 9
Praveen ThenrajE23 : Multi-Token PredictionTraining LLMs to predict multiple tokens helps to improve sampling efficiency, arithmetic reasoning abilities and code generation quality…May 19May 19
Praveen ThenrajinResearch Papers SummarizedE22 : TIES MergingRetaining only the top-k% influential parameter values and electing the signs for these values and then calculating mean, when merging…Apr 26Apr 26
Praveen ThenrajinResearch Papers SummarizedE21 : Adaptive RAGUnderstanding the complexity of user question, to identify a suitable approach to answer the question helps improve the effectiveness and…Apr 14Apr 14
Praveen ThenrajinResearch Papers SummarizedE20 : Chain-of-TableDynamically planning, resulting in transformed tables that are used in the chain of reasoning steps help improve the reasoning abilities…Apr 7Apr 7
Praveen ThenrajinResearch Papers SummarizedE19 : RAFT - Retrieval Augmented Fine TuningPaper Name : RAFT: Adapting Language Model to Domain Specific RAGMar 24Mar 24
Praveen ThenrajinResearch Papers SummarizedE18 : Simple Synthetic Data Reduces Sycophancy in LLMsUsing a simple template-based synthetic data generated to fine-tune LLMs, helps in reducing the sycophantic behaviour of LLMsFeb 3Feb 3
