add

app.py

@@ -9,6 +9,7 @@ from src.about import (
     CITATION_BUTTON_TEXT,
     EVALUATION_QUEUE_TEXT,
     INTRODUCTION_TEXT,
+    TASK_TEXT,
     LLM_BENCHMARKS_TEXT,
     TITLE,
 )
@@ -116,6 +117,8 @@ with demo:
             # leaderboard = init_leaderboard(LEADERBOARD_DF)
             with gr.Tabs():
                 for i, t in enumerate(task):
+                    if TASK_TEXT.get(t, None):
+                        gr.Markdown(TASK_TEXT[t], elem_classes="markdown-text")
                     with gr.TabItem(t.replace("_", " "), elem_id=f"llm-benchmark-tab-table-{t}", id=i):
                         leaderboard = init_leaderboard(leaderboard_dict[t])
                         gr.Row(leaderboard)

src/about.py

@@ -45,7 +45,16 @@ INTRODUCTION_TEXT = """
 <strong>LR<sup>2</sup>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<sup>2</sup>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.
 """
 
-
+TASK_TEXT = {
+    {
+        'Acrostic': 'The Acrostic task involves word clues like Crossword, but its objective is to form a hidden quotation or sentence from the answers to the clues. This requires that the answer words not only satisfy the corresponding clues but also effectively integrate to construct the ultimate hidden message. We collected 50 easy and 50 hard Acrostic samples from <a href="https://www.printable-puzzles.com/printable-acrostic-puzzles.php" target="_blank"> Printable Puzzles</a> with timestamps ranging from September 2024 to December 2024.',
+        'Crossword': 'The Crossword task requires inferring correct words from given clues and filling them into a grid. A key challenge lies in satisfying the constraint of shared letter intersections between horizontal and vertical words. We collected 150 Crossword samples published in 2024 from <a href="https://www.latimes.com" target="_blank"> Los Angeles Times</a> and <a href="https://www.vulture.com" target="_blank"> Vulture</a> in three sizes: $5\\times5$, $10\\times10$, and $15\\times15$, with 50 ones for each size.',
+        'Logic_Puzzle': 'The Logic Puzzle task constitutes a problem that necessitates logical reasoning to deduce relationships between a set of entities based on the given constraints and clues. The objective is to systematically analyze the given information, employing techniques such as hypothesis formation, elimination, and deductive inference, to determine a unique solution that satisfies all given constraints. We collected 50 puzzles for each of the four sizes ($4\\times4$, $4\\times5$, $4\\times6$, and $4\\times7$) from <a href="https://www.printable-puzzles.com/printable-logic-puzzles.php" target="_blank"> Printable Puzzles</a>, with timestamps ranging from September 2024 to December 2024.',
+        'Cryptogram': 'The Cryptogram task involves the decryption of an encrypted quotation or sentence, where each letter of an original text is substituted with another, resulting in an apparently nonsense text. Decryption requires identifying patterns, common letter frequencies, and word structures to deduce the letter-to-letter correspondences, ultimately reconstructing the original content. We collected 50 easy and 50 hard samples from <a href="https://www.printable-puzzles.com/printable-cryptograms.php" target="_blank"> Printable Puzzles</a> with timestamps ranging from September 2024 to December 2024.',
+        'Sudoku': 'The Sudoku task consists of filling a \\( n^2 \\times n^2 \\) grid with digits from \\( 1 \\) to \\( n^2 \\), subject to the constraint that each row, column, and \\( n \\times n \\) subgrid contains all digits from 1 to \\( n^2 \\) without repetition. Success in Sudoku relies on logical deduction and careful consideration of the existing digits to determine valid placements for the remaining numbers. From <a href="https://1sudoku.com" target="_blank"> 1sudoku</a>, we collected 200 Sudoku samples in total: 50 easy and 50 hard samples for both \\( 4\\times4 \\) and \\( 9\\times9 \\) sizes.',
+        'Drop_Quote': 'The Drop Quote task comprises a grid of multiple rows and columns, with each column providing a set of candidate letters. The task requires determining the correct row for letters in each column, effectively "dropping" it into target place to reveal the hidden quotation. We created 50 easy samples by manually compiling common quotations, and collected 50 hard samples from <a href="https://www.printable-puzzles.com/printable-drop-quotes.php" target="_blank"> Printable Puzzles</a>, with timestamps ranging from September 2024 to December 2024.'
+    }
+}
 
 # Which evaluations are you running? how can people reproduce what you have?
 LLM_BENCHMARKS_TEXT = f"""