Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@arXiv_csCL_bot@mastoxiv.page
2024-05-01 06:49:06

When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively
Tiziano Labruna, Jon Ander Campos, Gorka Azkune
arxiv.org/abs/2404.19705 arxiv.org/pdf/2404.19705
arXiv:2404.19705v1 Announce Type: new
Abstract: In this paper, we demonstrate how Large Language Models (LLMs) can effectively learn to use an off-the-shelf information retrieval (IR) system specifically when additional context is required to answer a given question. Given the performance of IR systems, the optimal strategy for question answering does not always entail external information retrieval; rather, it often involves leveraging the parametric memory of the LLM itself. Prior research has identified this phenomenon in the PopQA dataset, wherein the most popular questions are effectively addressed using the LLM's parametric memory, while less popular ones require IR system usage. Following this, we propose a tailored training approach for LLMs, leveraging existing open-domain question answering datasets. Here, LLMs are trained to generate a special token, , when they do not know the answer to a question. Our evaluation of the Adaptive Retrieval LLM (Adapt-LLM) on the PopQA dataset showcases improvements over the same LLM under three configurations: (i) retrieving information for all the questions, (ii) using always the parametric memory of the LLM, and (iii) using a popularity threshold to decide when to use a retriever. Through our analysis, we demonstrate that Adapt-LLM is able to generate the token when it determines that it does not know how to answer a question, indicating the need for IR, while it achieves notably high accuracy levels when it chooses to rely only on its parametric memory.

@arXiv_astrophGA_bot@mastoxiv.page
2024-04-24 07:31:15

Isochrone Fitting of Galactic Globular Clusters -- VI. High-latitude Clusters NGC5024 (M53), NGC5053, NGC5272 (M3), NGC5466, and NGC7099 (M30)
G. A. Gontcharov, S. S. Savchenko, A. A. Marchuk, C. J. Bonatto, O. S. Ryutina, M. Yu. Khovritchev, V. B. Il'in, A. V. Mosenkov, D. M. Poliakov, A. A. Smirnov
arxiv.org/abs/24…

@arXiv_condmatmtrlsci_bot@mastoxiv.page
2024-02-20 07:00:54

Influence of mechanical compliance of the substrate on the morphology of nanoporous gold thin films
Sadi Shahriar, Kavya Somayajula, Conner Winkeljohn, Jeremy Mason, Erkin Seker
arxiv.org/abs/2402.11694

@arXiv_eessIV_bot@mastoxiv.page
2024-02-15 07:20:30

A Comprehensive Review of Software and Hardware Energy Efficiency of Video Decoders
Matthias Kr\"anzler, Christian Herglotz, Andr\'e Kaup
arxiv.org/abs/2402.09001

@arXiv_csCL_bot@mastoxiv.page
2024-02-15 08:30:17

This arxiv.org/abs/2312.10323 has been replaced.
link: scholar.google.com/scholar?q=a

@arXiv_mathPR_bot@mastoxiv.page
2024-02-14 08:37:15

This arxiv.org/abs/2309.12055 has been replaced.
initial toot: mastoxiv.page/@arXiv_mat…

@arXiv_astrophGA_bot@mastoxiv.page
2024-02-12 07:04:03

Isochrone fitting of Galactic globular clusters -- V. NGC6397 and NGC6809 (M55)
George A. Gontcharov, Charles J. Bonatto, Olga S. Ryutina, Sergey S. Savchenko, Aleksandr V. Mosenkov, Vladimir B. Il'in, Maxim Yu. Khovritchev, Alexander A. Marchuk, Denis M. Poliakov, Anton A. Smirnov, Jonah Seguine
arxiv.org/abs/2402.0…

@arXiv_eessAS_bot@mastoxiv.page
2024-02-13 13:13:30

AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
Qian Yang, Jin Xu, Wenrui Liu, Yunfei Chu, Ziyue Jiang, Xiaohuan Zhou, Yichong Leng, Yuanjun Lv, Zhou Zhao, Chang Zhou, Jingren Zhou
arxiv.org/abs/2402.07729

@arXiv_mathPR_bot@mastoxiv.page
2024-02-14 08:37:15

This arxiv.org/abs/2309.12055 has been replaced.
initial toot: mastoxiv.page/@arXiv_mat…

@arXiv_astrophGA_bot@mastoxiv.page
2024-03-12 06:59:50

Velocity Dispersion of the open cluster NGC 2571 by Radial Velocities and Proper Motions
Maxim V. KuleshUral Fderal University, Aleksandra E. SamirkhanovaUral Federal University, Giovanni CarraroPadova University, Joao Sales SilvaObservatorio Nacional, Roberto Capuzzo DolcettaLa Sapienza University, Anton F. SeleznevUral Federal University