Langsung ke konten
Global sound
The Daily ML

The Daily ML

Ep48. Large Language Models Can Self-Improve in Long-context Reasoning

· 12 mnt

Catatan episode

This research paper investigates how large language models (LLMs) can improve their ability to reason over long contexts. The authors propose a self-improvement method called SEALONG that involves sampling multiple reasoning outputs from an LLM, scoring these outputs using Minimum Bayes Risk (MBR), and then fine-tuning the model using the highest-scoring outputs or by contrasting high-scoring and low-scoring outputs for preference optimization. Extensive experiments on several leading LLMs demonstrate that SEALONG effectively improves the long-context reasoning capabilities of LLMs without…

Situs: soundcloud.com

Live, satu jam terakhir: 12.026 lagu di 5.014 stasiun di 112 negara

Jelajahi dunia lewat radio

Cara lain untuk menjelajah (7)

Dengar sesuatu yang bagus? Simpan, atau langsung buka di Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
Radio JuvenilLanjut mendengarkan