Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 56

Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 192

Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 192

Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 202

Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 271

Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 271

Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 271

Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 271

Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 296

Warning: Undefined array key "abst" in /var/www/02search_html/bin/keyword.php on line 315
IEICE Trans

Keyword : GRPO


A Comparative Study of Reward Functions in Learning Prompt-Based Length Control of LLMs via GRPO
Hayato FUJIKOSHI Takeshi OKADOME 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2026/05/01
Vol. E109-D  No. 5 ; pp. 695-706
Type of Manuscript:  PAPER
Category: Natural Language Processing
Keyword: 
large language modelsoutput length controlreward function designGRPO
 Summary | Full Text:PDF