Hugging Face's logo

Spaces:
THUIR
/
AEOLLM
Running

App Files Community
陈俊杰 commited on
Commit
6c68509
·
1 Parent(s): e46b355

1230

Browse files
Files changed (1) hide show
  1. app.py +56 -14
app.py CHANGED
@@ -265,43 +265,85 @@ elif page == "LeaderBoard":
265
  "Spearman (Non-Factoid QA)": [],
266
  }
267
 
268
- TeamId = ["baseline", "baseline", "baseline", "baseline", 'ISLab', 'ISLab', 'ISLab', 'ISLab', 'default5', 'default5', 'default5', 'default5', 'default5', 'default5', 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR'],
269
- Methods = ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o", "llama3-1_baseline5", "llama3-1_baseline6", "llama3-1-baseline7", "llama3-2-baseline", "llm", "baselinev00", "baselinev02", "baselinev72r1", "baselinev70r1", "baselinev72r2", 'bert-base-uncased', 'gpt35turbo', 'logisticRegression', 'paraphrase-MiniLM-L6-v2']
 
 
 
 
 
 
270
 
271
  # teamId 唯一标识码
272
  DG = {
273
  "TeamId": TeamId,
274
  "Methods": Methods,
275
- "Accuracy": [0.5806, 0.5483, 0.6001, 0.6472, 0, 0, 0, 0, 0.6504481792717087, 0.5816503267973856, 0.631700513538749, 0.7111356209150326, 0.6176633986928104, 0.735954715219421, 0.5073529411764706, 0.5104038281979459, 0.5405182072829132, 0.5156874416433239],
276
- "Kendall's Tau": [0.3243, 0.1739, 0.3042, 0.4167, 0, 0, 0, 0, 0.4034134076281578, 0.25873621367415467, 0.38961572200778516, 0.5285302196320519, 0.31022946186879186, 0.5974703857412484, 0.024753688574416864, 0.2838365040871617, 0.18291748486237186, 0.334110095650077],
277
- "Spearman": [0.3505, 0.1857, 0.3264, 0.4512, 0, 0, 0, 0, 0.4303514807222638, 0.28208851475394925, 0.4200280894403279, 0.5723981513727318, 0.3392536955889527, 0.6542301178956093, 0.02673703949665616, 0.3132279427962962, 0.19244600211698878, 0.3697144425033483],
 
 
 
 
 
 
 
 
 
278
  }
279
  df1 = pd.DataFrame(DG)
280
 
281
  TE = {
282
  "TeamId": TeamId,
283
  "Methods": Methods,
284
- "Accuracy": [0.5107, 0.5050, 0.5461, 0.5581, 0.5067545088210725, 0.4766805549971185, 0, 0, 0.511188817632316, 0.5369175431336809, 0.570425718931911, 0.5518648601785212, 0.5162097017834246, 0.5757498972475753, 0.49544642857142857, 0.506452190525333, 0.5427970103511899, 0.5491338026438646],
285
- "Kendall's Tau": [0.1281, 0.0635, 0.2716, 0.3864, 0.18884532500063825, 0.31629653258509166, 0, 0, 0.10828008098753536, 0.26854542496891, 0.42340286124586973, 0.42163723763190575, 0.3111422734769831, 0.46417209045053276, 0.04074528095431955, 0.3533564092679483, 0.19204956587442087, 0.24122049643546917],
286
- "Spearman": [0.1352, 0.0667, 0.2867, 0.4157, 0.2033137543983765, 0.35189638758373964, 0, 0, 0.11421806788123415, 0.2820788649343955, 0.44950359766748854, 0.4567231163496956, 0.3284040387552273, 0.5061135134678696, 0.04302709609666947, 0.3758784332521168, 0.2019542748712654, 0.25105320709917717],
 
 
 
 
 
 
 
 
 
287
  }
288
  df2 = pd.DataFrame(TE)
289
 
290
  SG = {
291
  "TeamId": TeamId,
292
  "Methods": Methods,
293
- "Accuracy": [0.6504, 0.6014, 0.7162, 0.7441, 0.7518953983108395, 0.7870818213649097, 0.6187623875307698, 0.8003185213479332, 0.7007955341227401, 0.7519048414820473, 0.7477385992275697, 0.7969309163059164, 0.784410942407266, 0.769276748578219, 0.5, 0.7231299072659366, 0.5, 0.7348077412783295],
294
- "Kendall's Tau": [0.3957, 0.2688, 0.5092, 0.5001, 0.5377072309689559, 0.5709963447418871, 0.30897221697376714, 0.6064826537169805, 0.4819411311747811, 0.4874144871543796, 0.49885108461595573, 0.5408319381088115, 0.566750311845092, 0.539144026776003, 0.0, 0.48911130738063485, 0.0, 0.5436010461720943],
295
- "Spearman": [0.4188, 0.2817, 0.5403, 0.5405, 0.5830423197486431, 0.6276373633425562, 0.324348752437819, 0.6664032039425867, 0.5076789062134682, 0.539580429716673, 0.5603311161969196, 0.5987990693735654, 0.6200483357955027, 0.6021636544977567, 0.0, 0.530151784406405, 0.0, 0.5767282714406644],
 
 
 
 
 
 
 
 
 
296
  }
297
  df3 = pd.DataFrame(SG)
298
 
299
  NFQA = {
300
  "TeamId": TeamId,
301
  "Methods": Methods,
302
- "Accuracy": [0.5935, 0.5817, 0.7000, 0.7203, 0, 0, 0, 0, 0.5922294372294372, 0.7146378968253966, 0.7215900072150073, 0.7137157287157287, 0.7298538961038961, 0.7578841991341992, 0.6365868506493507,0.5985240800865801, 0.5590909090909092, 0.6762518037518037],
303
- "Kendall's Tau": [0.2332, 0.2389, 0.4440, 0.4235, 0, 0, 0, 0, 0.1701874070113157, 0.44019963513470517, 0.49445393416475697, 0.40897219553585185, 0.39880657282887155, 0.4594680081243032, 0.402354630029616, 0.29538507694084404, 0.10735098173126541, 0.4077804758055409],
304
- "Spearman": [0.2443, 0.2492, 0.4630, 0.4511, 0, 0, 0, 0, 0.18058287732894646, 0.4592548426675891, 0.5214865171404164, 0.4479941149402397, 0.424528242404003, 0.49907660929552167, 0.41802883351668096, 0.31033689944001186, 0.1096152564140644, 0.43265604612874153],
 
 
 
 
 
 
 
 
 
305
  }
306
  df4 = pd.DataFrame(NFQA)
307
 
 
265
  "Spearman (Non-Factoid QA)": [],
266
  }
267
 
268
+ TeamId = ["baseline", "baseline", "baseline", "baseline",
269
+ 'ISLab', 'ISLab', 'ISLab', 'ISLab',
270
+ 'default5', 'default5', 'default5', 'default5',
271
+ 'KNUIR', 'KNUIR', 'KNUIR', 'KNUIR'],
272
+ Methods = ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o",
273
+ "llama3-1_baseline5", "llama3-1_baseline6", "llama3-1-baseline7", "llama3-2-baseline",
274
+ "baselinev02", "baselinev72r1", "baselinev70r1", "baselinev72r2",
275
+ 'bert-base-uncased', 'gpt35turbo', 'logisticRegression', 'paraphrase-MiniLM-L6-v2']
276
 
277
  # teamId 唯一标识码
278
  DG = {
279
  "TeamId": TeamId,
280
  "Methods": Methods,
281
+ "Accuracy": [0.5806, 0.5483, 0.6001, 0.6472,
282
+ 0, 0, 0, 0,
283
+ 0.631700513538749, 0.7111356209150326, 0.6176633986928104, 0.735954715219421,
284
+ 0.5073529411764706, 0.5104038281979459, 0.5405182072829132, 0.5156874416433239],
285
+ "Kendall's Tau": [0.3243, 0.1739, 0.3042, 0.4167,
286
+ 0, 0, 0, 0,
287
+ 0.38961572200778516, 0.5285302196320519, 0.31022946186879186, 0.5974703857412484,
288
+ 0.024753688574416864, 0.2838365040871617, 0.18291748486237186, 0.334110095650077],
289
+ "Spearman": [0.3505, 0.1857, 0.3264, 0.4512,
290
+ 0, 0, 0, 0,
291
+ 0.4200280894403279, 0.5723981513727318, 0.3392536955889527, 0.6542301178956093,
292
+ 0.02673703949665616, 0.3132279427962962, 0.19244600211698878, 0.3697144425033483],
293
  }
294
  df1 = pd.DataFrame(DG)
295
 
296
  TE = {
297
  "TeamId": TeamId,
298
  "Methods": Methods,
299
+ "Accuracy": [0.5107, 0.5050, 0.5461, 0.5581,
300
+ 0.5067545088210725, 0.4766805549971185, 0, 0,
301
+ 0.570425718931911, 0.5518648601785212, 0.5162097017834246, 0.5757498972475753,
302
+ 0.49544642857142857, 0.506452190525333, 0.5427970103511899, 0.5491338026438646],
303
+ "Kendall's Tau": [0.1281, 0.0635, 0.2716, 0.3864,
304
+ 0.18884532500063825, 0.31629653258509166, 0, 0,
305
+ 0.42340286124586973, 0.42163723763190575, 0.3111422734769831, 0.46417209045053276,
306
+ 0.04074528095431955, 0.3533564092679483, 0.19204956587442087, 0.24122049643546917],
307
+ "Spearman": [0.1352, 0.0667, 0.2867, 0.4157,
308
+ 0.2033137543983765, 0.35189638758373964, 0, 0,
309
+ 0.44950359766748854, 0.4567231163496956, 0.3284040387552273, 0.5061135134678696,
310
+ 0.04302709609666947, 0.3758784332521168, 0.2019542748712654, 0.25105320709917717],
311
  }
312
  df2 = pd.DataFrame(TE)
313
 
314
  SG = {
315
  "TeamId": TeamId,
316
  "Methods": Methods,
317
+ "Accuracy": [0.6504, 0.6014, 0.7162, 0.7441,
318
+ 0.7518953983108395, 0.7870818213649097, 0.6187623875307698, 0.8003185213479332,
319
+ 0.7477385992275697, 0.7969309163059164, 0.784410942407266, 0.769276748578219,
320
+ 0.5, 0.7231299072659366, 0.5, 0.7348077412783295],
321
+ "Kendall's Tau": [0.3957, 0.2688, 0.5092, 0.5001,
322
+ 0.5377072309689559, 0.5709963447418871, 0.30897221697376714, 0.6064826537169805,
323
+ 0.49885108461595573, 0.5408319381088115, 0.566750311845092, 0.539144026776003,
324
+ 0.0, 0.48911130738063485, 0.0, 0.5436010461720943],
325
+ "Spearman": [0.4188, 0.2817, 0.5403, 0.5405,
326
+ 0.5830423197486431, 0.6276373633425562, 0.324348752437819, 0.6664032039425867,
327
+ 0.5603311161969196, 0.5987990693735654, 0.6200483357955027, 0.6021636544977567,
328
+ 0.0, 0.530151784406405, 0.0, 0.5767282714406644],
329
  }
330
  df3 = pd.DataFrame(SG)
331
 
332
  NFQA = {
333
  "TeamId": TeamId,
334
  "Methods": Methods,
335
+ "Accuracy": [0.5935, 0.5817, 0.7000, 0.7203,
336
+ 0, 0, 0, 0,
337
+ 0.7215900072150073, 0.7137157287157287, 0.7298538961038961, 0.7578841991341992,
338
+ 0.6365868506493507,0.5985240800865801, 0.5590909090909092, 0.6762518037518037],
339
+ "Kendall's Tau": [0.2332, 0.2389, 0.4440, 0.4235,
340
+ 0, 0, 0, 0,
341
+ 0.49445393416475697, 0.40897219553585185, 0.39880657282887155, 0.4594680081243032,
342
+ 0.402354630029616, 0.29538507694084404, 0.10735098173126541, 0.4077804758055409],
343
+ "Spearman": [0.2443, 0.2492, 0.4630, 0.4511,
344
+ 0, 0, 0, 0,
345
+ 0.5214865171404164, 0.4479941149402397, 0.424528242404003, 0.49907660929552167,
346
+ 0.41802883351668096, 0.31033689944001186, 0.1096152564140644, 0.43265604612874153],
347
  }
348
  df4 = pd.DataFrame(NFQA)
349