Auto. Make Doomgrad HF Review on 20 January

averkij · Jan 20, 2025 · 659d653 · 659d653
1 parent b7f9efc
commit 659d653
Show file tree

Hide file tree

Showing 10 changed files with 494 additions and 835 deletions.
diff --git a/assets/img_data/2501.10132.json b/assets/img_data/2501.10132.json
@@ -0,0 +1,110 @@
+[
+    {
+        "header": "Abstract",
+        "images": []
+    },
+    {
+        "header": "1Introduction",
+        "images": [
+            {
+                "img": "https://arxiv.org/html/2501.10132/x1.png",
+                "caption": "Figure 1:(a) Simple Function Calling. (b) Complex Function Calling withmulti-step,constraints,parameter value reasoning,long parameter valuesandlong context. Different colors correspond to the corresponding features marked in the figure.",
+                "position": 159
+            },
+            {
+                "img": "https://arxiv.org/html/2501.10132/x2.png",
+                "caption": "Figure 2:Overview of the data collection process. (a) is the high-level process of data collection. (b) is the example of human correction process.(c) is the example of disambiguation process. Thegreypart is removed during annotation. A detailed annotation example is shown in AppendixA.1.",
+                "position": 248
+            }
+        ]
+    },
+    {
+        "header": "2ComplexFuncBench",
+        "images": [
+            {
+                "img": "https://arxiv.org/html/2501.10132/x3.png",
+                "caption": "Figure 3:Overview ofComplexEval. Different colors represent different API response types. Colorbluerepresents format error with specific error message. Colorgreenrepresents correct function call with corresponding golden API response. Colorredrepresents invalid function call with general error message.",
+                "position": 337
+            }
+        ]
+    },
+    {
+        "header": "3ComplexEval: Automatic Evaluation",
+        "images": []
+    },
+    {
+        "header": "4Experiments",
+        "images": [
+            {
+                "img": "https://arxiv.org/html/2501.10132/extracted/6138262/images/error_analysis.png",
+                "caption": "Figure 4:Error type analysis for different models.",
+                "position": 725
+            },
+            {
+                "img": "https://arxiv.org/html/2501.10132/extracted/6138262/images/value_error_distribution.png",
+                "caption": "Figure 5:Error rates for each parameter type of different models",
+                "position": 734
+            },
+            {
+                "img": "https://arxiv.org/html/2501.10132/x4.png",
+                "caption": "Figure 6:Function calling steps distribution.",
+                "position": 747
+            }
+        ]
+    },
+    {
+        "header": "5Related Work",
+        "images": []
+    },
+    {
+        "header": "6Conclusion",
+        "images": []
+    },
+    {
+        "header": "References",
+        "images": []
+    },
+    {
+        "header": "Appendix AData Annotation",
+        "images": []
+    },
+    {
+        "header": "Appendix BAutomatic Evaluation",
+        "images": [
+            {
+                "img": "https://arxiv.org/html/2501.10132/x5.png",
+                "caption": "Figure 7:An example for golden function call updating. Path on the left is the annotated shortest function call path with three steps.",
+                "position": 1217
+            },
+            {
+                "img": "https://arxiv.org/html/2501.10132/x6.png",
+                "caption": "Figure 8:Prompt for Query Generation.",
+                "position": 1487
+            },
+            {
+                "img": "https://arxiv.org/html/2501.10132/x7.png",
+                "caption": "Figure 9:Prompt for Query Generalization.",
+                "position": 1490
+            },
+            {
+                "img": "https://arxiv.org/html/2501.10132/x8.png",
+                "caption": "Figure 10:Prompt for LLM-based Match.",
+                "position": 1493
+            },
+            {
+                "img": "https://arxiv.org/html/2501.10132/x9.png",
+                "caption": "Figure 11:Prompt for Completeness Evaluation.",
+                "position": 1496
+            },
+            {
+                "img": "https://arxiv.org/html/2501.10132/x10.png",
+                "caption": "Figure 12:Prompt for Correctness Evaluation.",
+                "position": 1499
+            }
+        ]
+    },
+    {
+        "header": "Appendix CParameter Type Examples",
+        "images": []
+    }
+]
diff --git a/assets/json/2501.10132.json b/assets/json/2501.10132.json
diff --git a/assets/pdf/title_img/2501.10132.jpg b/assets/pdf/title_img/2501.10132.jpg
diff --git a/d/2025-01-20.html b/d/2025-01-20.html
diff --git a/d/2025-01-20.json b/d/2025-01-20.json
diff --git a/hf_papers.json b/hf_papers.json
diff --git a/index.html b/index.html
diff --git a/log.txt b/log.txt
@@ -1,3 +1,3 @@
-[20.01.2025 02:10] Read previous papers.
-[20.01.2025 02:10] Generating top page (month).
-[20.01.2025 02:10] Writing top page (month).
+[20.01.2025 03:13] Read previous papers.
+[20.01.2025 03:13] Generating top page (month).
+[20.01.2025 03:13] Writing top page (month).