Spaces:
Running
Running
Commit
·
b6609fd
1
Parent(s):
a7449d7
add
Browse files- index.html +1 -1
index.html
CHANGED
|
@@ -147,7 +147,7 @@ tr:hover a {
|
|
| 147 |
<body>
|
| 148 |
<h1>LR\({}^{2}\)Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems</h1>
|
| 149 |
<p>
|
| 150 |
-
|
| 151 |
</p>
|
| 152 |
<hr />
|
| 153 |
|
|
|
|
| 147 |
<body>
|
| 148 |
<h1>LR\({}^{2}\)Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems</h1>
|
| 149 |
<p>
|
| 150 |
+
<strong>LR\({}^{2}\)Bench</strong> is a novel benchmark designed to evaluate the <strong>L</strong>ong-chain <strong>R</strong>eflective <strong>R</strong>easoning capabilities of LLMs. LR\({}^{2}\)Bench comprises 850 samples across six Constraint Satisfaction Problems (CSPs) where reflective reasoning is crucial for deriving solutions that meet all given constraints. Each type of task focuses on distinct constraint patterns, such as knowledge-based, logical, and spatial constraints, providing a comprehensive evaluation of diverse problem-solving scenarios.
|
| 151 |
</p>
|
| 152 |
<hr />
|
| 153 |
|