From 239dc2e89a46c60e406c04ed2f188812a553e56d Mon Sep 17 00:00:00 2001 From: lr-tsinghua11 Date: Sat, 21 Oct 2023 01:26:22 +0800 Subject: [PATCH] fix typo --- docs/index.html | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) diff --git a/docs/index.html b/docs/index.html index 6c66fa7..974e80c 100644 --- a/docs/index.html +++ b/docs/index.html @@ -83,57 +83,48 @@

Aohan Zeng†§*,†§*, Mingdao Liu†*, + >†*, Rui Lu†*, + >†*, Bowen Wang†, + >†, Xiao Liu†§, + >†§, Yuxiao Dong†, + >†, Jie Tang† + >† @@ -142,9 +133,14 @@

†Tsinghua University, §Zhipu.AI
*Equal contirubtion
*Equal contribution +
1Work is done during the internship in + Zhipu.AI of Mingdao Liu, Rui Lu, Bowen Wang -
1Work is done during the internship in Zhipu.AI of Mingdao Liu, Rui Lu, Bowen Wang @@ -767,7 +763,15 @@

Case Study


-

Comparison case study on ALFWorld and Knowledge Graph between Llama-2-70b-chat and AgentLM-70B. (a) For the ALFWorld task, Llama-2-70b-chat repeated the same action ultimately failing to complete the task, while Agent-70B adjusted its actions after a failure. (b) For the Knowledge Graph task, Llama-2-70b-chat refused to fix the function call and instead demanded the user to implement the function upon encountering a error. In contrast, AgentLM-70B provided the correct function call. +

+ Comparison case study on ALFWorld and Knowledge Graph between + Llama-2-70b-chat and AgentLM-70B. (a) For the ALFWorld task, + Llama-2-70b-chat repeated the same action ultimately failing to + complete the task, while Agent-70B adjusted its actions after a + failure. (b) For the Knowledge Graph task, Llama-2-70b-chat refused + to fix the function call and instead demanded the user to implement + the function upon encountering a error. In contrast, AgentLM-70B + provided the correct function call.