research-papers

research-papers

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

Original Paper: https://arxiv.org/abs/2407.08223 By: Zilong Wang, Zifeng Wang, Long Le, Huaixiu Steven Zheng, Swaroop Mishra, Vincent Perot, Yuwei Zhang, Anush Mattapalli, Ankur Taly, Jingbo Shang, Chen-Yu Lee, Tomas Pfister Abstract: Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external

research-papers

Distilling System 2 into System 1

Original Paper: https://arxiv.org/abs/2407.06023v1 By: Ping Yu, Jing Xu, Jason Weston, Ilia Kulikov Abstract: Large language models (LLMs) can spend extra compute during inference to generate intermediate thoughts, which helps to produce better final responses. Since Chain-of-Thought (Wei et al., 2022), many such System 2 techniques

research-papers

Tree Search For Language Model Agents

Original Paper: https://jykoh.com/search-agents By: Jing Yu Koh, Stephen McAleer, Daniel Fried, Ruslan Salakhutdinov Abstract: Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a fundamental challenge remains: LMs, primarily optimized for natural language understanding

research-papers

RouteLLM: Learning to Route LLMs with Preference Data

Original Paper: https://arxiv.org/abs/2406.18665v2 By: Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E. Gonzalez, M Waleed Kadous, Ion Stoica Abstract: Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often

research-papers

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems

Original Paper: https://arxiv.org/abs/2407.01370 By: Philippe Laban, Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu Abstract: LLMs and RAG systems are now capable of handling millions of input tokens or more. However, evaluating the output quality of such systems on long-context tasks remains challenging, as tasks like

research-papers

Exploring Advanced Large Language Models with LLMsuite

Original Paper: https://arxiv.org/abs/2407.12036 By: Giorgio Roffo Abstract: This tutorial explores the advancements and challenges in the development of Large Language Models (LLMs) such as ChatGPT and Gemini. It addresses inherent limitations like temporal knowledge cutoffs, mathematical inaccuracies, and the generation of incorrect information, proposing solutions

research-papers

LLM Critics Help Catch LLM Bugs

Original Paper: https://cdn.openai.com/llm-critics-help-catch-llm-bugs-paper.pdf By: OpenAI Abstract: Reinforcement learning from human feedback (RLHF) is fundamentally limited by the capacity of humans to correctly evaluate model output. To improve human evaluation ability and overcome that limitation this work trains “critic” models that help humans to more accurately

research-papers

From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data

Original Paper: https://arxiv.org/abs/2406.19292 By: Zheyang Xiong, Vasilis Papageorgiou, Kangwook Lee, Dimitris Papailiopoulos Abstract: Recent studies have shown that Large Language Models (LLMs) struggle to accurately retrieve information and maintain reasoning capabilities when processing long-context inputs. To address these limitations, we propose a finetuning approach utilizing

research-papers

Following Length Constraints in Instructions

Original Paper: https://arxiv.org/abs/2406.17744 By: Weizhe Yuan, Ilia Kulikov, Ping Yu, Kyunghyun Cho, Sainbayar Sukhbaatar, Jason Weston, Jing Xu Abstract: Aligned instruction following models can better fulfill user requests than their unaligned counterparts. However, it has been shown that there is a length bias in evaluation

research-papers

CodeGemma: Open Code Models Based on Gemma

Original Paper: https://arxiv.org/abs/2406.11409 By: CodeGemma Team: Heri Zhao, Jeffrey Hui, Joshua Howland, Nam Nguyen, Siqi Zuo, Andrea Hu, Christopher A. Choquette-Choo, Jingyue Shen, Joe Kelley, Kshitij Bansal, Luke Vilnis, Mateo Wirth, Paul Michel, Peter Choy, Pratik Joshi, Ravin Kumar, Sarmad Hashmi, Shubham Agrawal, Zhitao Gong,

research-papers

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models

Original Paper: https://arxiv.org/abs/2307.08303 By: Zhiyuan Peng, Xuyang Wu, Qifan Wang, Yi Fang Abstract: Dense retrieval (DR) converts queries and documents into dense embeddings and measures the similarity between queries and documents in vector space. One of the challenges in DR is the lack of domain-specific

research-papers

PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers

Original Paper: https://arxiv.org/abs/2406.12430 By: Myeonghwa Lee, Seonho An, Min-Soo Kim Abstract: In this paper, we conduct a study to utilize LLMs as a solution for decision making that requires complex data analysis. We define Decision QA as the task of answering the best decision, dbest,