-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathindex.html
727 lines (639 loc) · 40 KB
/
index.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<meta name="description" content="DESCRIPTION META TAG" />
<meta property="og:title" content="SOCIAL MEDIA TITLE TAG" />
<meta
property="og:description"
content="SOCIAL MEDIA DESCRIPTION TAG TAG"
/>
<meta property="og:url" content="URL OF THE WEBSITE" />
<meta
property="og:image"
content="static/image/your_banner_image.png"
/>
<meta property="og:image:width" content="1200" />
<meta property="og:image:height" content="630" />
<meta name="twitter:title" content="TWITTER BANNER TITLE META TAG" />
<meta
name="twitter:description"
content="TWITTER BANNER DESCRIPTION META TAG"
/>
<meta
name="twitter:image"
content="static/images/your_twitter_banner_image.png"
/>
<meta name="twitter:card" content="summary_large_image" />
<meta name="keywords" content="KEYWORDS SHOULD BE PLACED HERE" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Large Language Diffusion Models</title>
<link
href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro"
rel="stylesheet"
/>
<link rel="stylesheet" href="static/css/bulma.min.css" />
<link rel="stylesheet" href="static/css/bulma-carousel.min.css" />
<link rel="stylesheet" href="static/css/bulma-slider.min.css" />
<link rel="stylesheet" href="static/css/fontawesome.all.min.css" />
<link
rel="stylesheet"
href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css"
/>
<link rel="stylesheet" href="static/css/index.css" />
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script src="https://documentcloud.adobe.com/view-sdk/main.js"></script>
<script defer src="static/js/fontawesome.all.min.js"></script>
<script src="static/js/bulma-carousel.min.js"></script>
<script src="static/js/bulma-slider.min.js"></script>
<script src="static/js/index.js"></script>
<script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
</head>
<body>
<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">
Large Language Diffusion Models
</h1>
<div class="is-size-5 publication-authors">
<span class="author-block">
<a
href="https://scholar.google.com/citations?user=mVaNdrsAAAAJ"
target="_blank"
>Shen Nie</a
><sup>1</sup>,</span
>
<span class="author-block">
<a href="" target="_blank">Fengqi Zhu</a
><sup>1</sup>,</span
>
<span class="author-block">
<a
href="https://yyyouy.github.io/"
target="_blank"
>Zebin You</a
><sup>1</sup>,</span
>
<span class="author-block">
<a
href="https://scholar.google.com/citations?user=cAz9PToAAAAJ"
target="_blank"
>Xiaolu Zhang</a
><sup>2</sup>,</span
>
<span class="author-block">
<a href="" target="_blank">Jingyang Ou</a
><sup>1</sup>,</span
>
<span class="author-block">
<a href="" target="_blank">Jun Hu</a
><sup>2</sup>,</span
>
<span class="author-block">
<a
href="https://scholar.google.com/citations?user=mCVvloEAAAAJ"
target="_blank"
>Jun Zhou</a
><sup>2</sup>,</span
>
<span class="author-block">
<a
href="https://scholar.google.com/citations?user=j8K1FqEAAAAJ"
target="_blank"
>Yankai Lin</a
><sup>1</sup>,</span
>
<span class="author-block">
<a
href="https://scholar.google.com/citations?user=tbxCHJgAAAAJ"
target="_blank"
>Ji-Rong Wen</a
><sup>1</sup>,</span
>
<span class="author-block">
<a
href="https://zhenxuan00.github.io/"
target="_blank"
>Chongxuan Li</a
><sup>1</sup></span
>
</div>
<div class="is-size-5 publication-authors">
<span class="author-block"
><sup>1</sup>Renmin University of
China,</span
>
<span class="author-block"
><sup>2</sup>Ant Group</span
>
</div>
<div class="column has-text-centered">
<div class="publication-links">
<span class="link-block">
<a
href="http://arxiv.org/abs/2502.09992"
target="_blank"
class="external-link button is-normal is-rounded is-dark"
>
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Paper</span>
</a>
</span>
<span class="link-block">
<a
href="https://github.com/ML-GSAI/LLaDA"
target="_blank"
class="external-link button is-normal is-rounded is-dark"
>
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code</span>
</a>
</span>
<span class="link-block">
<a
href="https://huggingface.co/GSAI-ML"
target="_blank"
class="external-link button is-normal is-rounded is-dark"
>
<span class="icon">🤗</span>
<span>Model</span>
</a>
</span>
</div>
</div>
<p style="text-align: center; margin-top: 20px; font-size: 24px;">
<strong>TL;DR:</strong> <span style="color: #1E88E5;">We introduce LLaDA, a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance.
</span>
</p>
</div>
</div>
</div>
</div>
</section>
<section class="hero is-small">
<div class="hero-body">
<div
class="container"
style="
display: flex;
justify-content: center;
gap: 1px;
"
>
<div class="item" style="text-align: center">
<img
src="static/images/LLaDA_vs_LLaMA.svg"
alt="LLaDA_vs_LLaMA"
style="width: 75%; max-width: 1000px;"
/>
</div>
<div class="item" style="text-align: center">
<img
src="static/images/LLaDA_vs_LLaMA_chat.svg"
alt="LLaDA_vs_LLaMA_chat"
style="width: 75%; max-width: 1000px;"
/>
</div>
</div>
</div>
</section>
<section
class="section"
id="Intro"
style="text-align: center; font-weight: bold; position: relative; padding: 50px 20px;"
>
<div
style="
width: 100%;
height: 1px;
background-color: rgba(0, 0, 0, 0.1);
margin: 0 auto 15px auto;
"
></div>
<div
class="container is-max-desktop content"
style="position: relative; font-size: 1.8rem; color: #1E88E5; text-shadow: 2px 2px 5px rgba(0, 0, 0, 0.2); font-style: italic; font-family: 'Times New Roman', serif;"
>
What is now proved was once only imagined. ——— William Blake
</div>
<div
style="
position: absolute;
bottom: -10px;
right: 50px;
font-weight: bold;
font-size: 1rem;
color: #666;
font-style: italic;
"
>
</div>
</section>
<section class="section" id="Introduction">
<div class="container is-max-desktop content">
<h2 class="title" style="font-family: 'Times New Roman', serif;">
Motivation
</h2>
<p style="font-size: 1.6rem; font-family: 'Times New Roman', Times, serif;">
We contend that the intelligence of LLMs—manifested in <i>scalability</i>, <i>instruction-following</i>, <i>in-context learning</i>,
<i>conversational ability</i>, and <i>compression—stems</i> not from the autoregressive mechanism per se, but rather from
the core principle of generative modeling: approximating the true language distribution through maximum
likelihood estimation.
</p>
<p style="font-size: 1.6rem; font-family: 'Times New Roman', Times, serif;">
We introduce <b>LLaDA</b> (<b>L</b>arge <b>La</b>nguage <b>D</b>iffusion with m<b>A</b>sking), a simple yet principled
generative paradigm for large language models that demonstrates the aforementioned remarkable capabilities.
</p>
<h2 class="title" style="font-family: 'Times New Roman', serif;">
Method
</h2>
<p style="font-size: 1.6rem; font-family: 'Times New Roman', Times, serif;">
LLaDA is a masked diffusion model [1, 2, 3] that follows standard pretraining and SFT
while sampling via diffusion. During pretraining, it masks all tokens randomly
at ratio \( t ∼ U[0,1] \); in SFT, only response tokens may be masked. The model
simulates diffusion from full masking (\(t = 1\)) to unmasking (\(t = 0\)), predicting
all masks simultaneously at each step with flexible remasking.
</p>
</div>
<div class="container is-max-desktop content">
<img
src="static/images/method.svg"
alt="method"
style="width: 100%; height: auto; display: block; margin-bottom: 30px;"
/>
</div>
<div class="container is-max-desktop content">
<h2 class="title" style="font-family: 'Times New Roman', serif;">
Scalability
</h2>
<p style="font-size: 1.6rem; font-family: 'Times New Roman', Times, serif;">
LLaDA demonstrates impressive scalability, with its overall
trend being highly competitive with that of autoregressive baseline on the same data.
</p>
</div>
<div class="container is-max-desktop content">
<div class="row" style="display: flex; justify-content: center; gap: 20px;">
<img
src="static/images/scaling_mmlu.svg"
alt="scaling_mmlu"
style="
width: 30%;
height: auto;
margin-bottom: 20px;
"
/>
<img
src="static/images/scaling_arc_c.svg"
alt="scaling_arc_c"
style="width: 30%; height: auto; margin-bottom: 20px"
/>
<img
src="static/images/scaling_cmmlu.svg"
alt="scaling_cmmlu"
style="width: 30%; height: auto; margin-bottom: 20px"
/>
</div>
<div class="row" style="display: flex; justify-content: center; gap: 20px;">
<img
src="static/images/scaling_piqa.svg"
alt="scaling_piqa"
style="
width: 30%;
height: auto;
margin-bottom: 20px;
"
/>
<img
src="static/images/scaling_gsm8k.svg"
alt="scaling_gsm8k"
style="width: 30%; height: auto; margin-bottom: 20px"
/>
<img
src="static/images/scaling_humaneval.svg"
alt="scaling_humaneval"
style="width: 30%; height: auto; margin-bottom: 20px"
/>
</div>
</div>
</section>
<section class="section" id="Sampling Process">
<div
style="
width: 100%;
height: 1px;
background-color: rgba(0, 0, 0, 0.1);
margin: 0 auto 15px auto;
"
></div>
<div class="container is-max-desktop content">
<h2 class="title" style="font-family: 'Times New Roman', serif;">
A text generation method different from the traditional left-to-right approach
</h2>
<p style="font-size: 1.6rem; font-family: 'Times New Roman', Times, serif;">
Prompt: <i>Explain what artificial intelligence is.</i>
</p>
<img
src="static/images/diff_normal_150ms.gif"
alt="diff_normal_150ms.gif"
style="width: 100%; height: auto; display: block; margin-bottom: 10px; margin-left: auto; margin-right: auto;"
/>
</div>
</section>
<section class="section" id="Case study">
<div
style="
width: 100%;
height: 1px;
background-color: rgba(0, 0, 0, 0.1);
margin: 0 auto 15px auto;
"
></div>
<div class="container is-max-desktop content">
<h2 class="title" style="font-family: 'Times New Roman', serif;">
Case Studies
</h2>
<div style="width: 100%; font-family: 'Times New Roman', serif; border: 1px solid #ddd; border-radius: 8px; overflow: hidden; box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);">
<!-- Title Section -->
<div style="background-color: #f4f4f4; padding: 15px; font-weight: bold; text-align: center; border-bottom: 1px solid #ddd; font-size: 24px;">
Math problem
</div>
<!-- User and LLaDA-Instruct Sections -->
<div style="display: flex; flex-direction: column; padding: 20px;">
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Emma decides to run 4 sprints 5 times a week. She runs 75 meters each sprint. How many total meters does she run a week?
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Emma runs 4 sprints each time, so she runs a total of 4 x 5 = 20 sprints a week. Each sprint is 75 meters long, so Emma runs a total of 20 x 75 = 1500 meters a week. The final result is 1500.
</div>
</div>
</div>
</div>
<div style="width: 100%; font-family: 'Times New Roman', serif; border: 1px solid #ddd; border-radius: 8px; overflow: hidden; box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);">
<!-- Title Section -->
<div style="background-color: #f4f4f4; padding: 15px; font-weight: bold; text-align: center; border-bottom: 1px solid #ddd; font-size: 24px;">
Daily life
</div>
<!-- User and LLaDA-Instruct Sections -->
<div style="display: flex; flex-direction: column; padding: 20px;">
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Please recommend me three famous movies
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Certainly! Here are three famous movies that have achieved widespread popularity and critical acclaim: <br>
1. <b>The Shawshank Redemption</b> (1994) - Inspired by a novella and directed by Frank Darabont, this film tells the story of Andy Dufresne, a man convicted of murdering his wife, dealing with his harsh life in Shawshank Prison and forming an unlikely friendship with a fellow inmate. <br>
2. <b>The Godfather</b> (1972) - Directed by Francis Ford Coppola, this film is based on Mario Puzo's novel of the same name. It follows the story of the Corleone family, particularly Michael Corleone, who rises to power and takes over the family's criminal empire. <br>
3. <b>The Empire Strikes Back</b> (1980) - Directed by George Lucas, this film continues the story of a young Skywalker in the Star Wars saga. It follows Luke Skywalker as he helps the Rebel Alliance fight against the Galactic Empire and destroy the powerful weapon, the Death Star. <br>
All of these films are celebrated for their cinematic achievements, powerful storytelling, and memorable characters.
</div>
</div>
</div>
</div>
<div style="width: 100%; font-family: 'Times New Roman', serif; border: 1px solid #ddd; border-radius: 8px; overflow: hidden; box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);">
<!-- Title Section -->
<div style="background-color: #f4f4f4; padding: 15px; font-weight: bold; text-align: center; border-bottom: 1px solid #ddd; font-size: 24px;">
Code generation
</div>
<!-- User and LLaDA-Instruct Sections -->
<div style="display: flex; flex-direction: column; padding: 20px;">
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
I am writing python code, I have an array, please
help me sort it from largest to smallest
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Certainly! You can sort an array from the largest to
smallest in Python using the ‘sort()’ method or the
‘sorted()‘ function. Here’s an example: <br />
### Using ‘sort()’ method: <br />my array = [3, 1,
4, 1, 5, 2] <br />my array.sort(reverse=True)<br />
print(my array)
</div>
</div>
</div>
</div>
<div style="width: 100%; font-family: 'Times New Roman', serif; border: 1px solid #ddd; border-radius: 8px; overflow: hidden; box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);">
<!-- Title Section -->
<div style="background-color: #f4f4f4; padding: 15px; font-weight: bold; text-align: center; border-bottom: 1px solid #ddd; font-size: 24px;">
Translation (English → Chinese)
</div>
<!-- User and LLaDA-Instruct Sections -->
<div style="display: flex; flex-direction: column; padding: 20px;">
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Please help me translate into Chinese: ‘What is now proved was once only imagined’
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
现在被证明的曾经只是想象
</div>
</div>
</div>
</div>
<div style="width: 100%; font-family: 'Times New Roman', serif; border: 1px solid #ddd; border-radius: 8px; overflow: hidden; box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);">
<!-- Title Section -->
<div style="background-color: #f4f4f4; padding: 15px; font-weight: bold; text-align: center; border-bottom: 1px solid #ddd; font-size: 24px;">
Translation (English → German)
</div>
<!-- User and LLaDA-Instruct Sections -->
<div style="display: flex; flex-direction: column; padding: 20px;">
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Please help me translate into German: ‘What is now proved was once only imagined’
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Wer heute bestätigt ist, war einst nur immaginiert.
</div>
</div>
</div>
</div>
<div style="width: 100%; font-family: 'Times New Roman', serif; border: 1px solid #ddd; border-radius: 8px; overflow: hidden; box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);">
<!-- Title Section -->
<div style="background-color: #f4f4f4; padding: 15px; font-weight: bold; text-align: center; border-bottom: 1px solid #ddd; font-size: 24px;">
Multi-turn dialogue case 1
</div>
<!-- User and LLaDA-Instruct Sections -->
<div style="display: flex; flex-direction: column; padding: 20px;">
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Could you please share with me what the initial two lines of the renowned poem `The Road Not Taken'?
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Certainly! The initial two lines of the renowned poem ``The Road Not Taken" by Robert Frost are: ``Two roads diverged in a yellow wood,
And sorry I could not travel both." These lines set the stage for the poem, introducing the idea of a speaker facing a choice between two paths.
</div>
</div>
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Please help me translate into Chinese.
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Sure! The first two lines of ``The Road Not Taken" by Robert Frost can be translated into Chinese as:
``两条路分岔在黄色的树林中，遗憾我不能同时走''
</div>
</div>
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Please translate into German.
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Sure! The first two lines of ``The Road Not Taken" by Robert Frost can be translated into German as:
``Zwei Wege trennten sich im gelben Wald, und leider konnte ich nicht beide tun."
</div>
</div>
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Please also write a poem about life choices. I require 5 sentences, and the first word of each sentence starts with C as the first letter.
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Certainly! Here's a poem about life choices, with each sentence starting with the letter ``C":
Choices cascade through life's journey, Creating connections with each decision, Careful
consideration leads to better paths, Courageous choices shape our destiny, Choosing wisely guides us through the years.
</div>
</div>
</div>
</div>
<div style="width: 100%; font-family: 'Times New Roman', serif; border: 1px solid #ddd; border-radius: 8px; overflow: hidden; box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);">
<!-- Title Section -->
<div style="background-color: #f4f4f4; padding: 15px; font-weight: bold; text-align: center; border-bottom: 1px solid #ddd; font-size: 24px;">
Multi-turn dialogue case 2
</div>
<!-- User and LLaDA-Instruct Sections -->
<div style="display: flex; flex-direction: column; padding: 20px;">
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May.
How many clips did Natalia sell altogether in April and May?
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Natalia sold clips to 48 friends in April. She sold half as many clips in May, so she sold 48/2 = 24 clips in May.
Altogether, Natalia sold 48 + 24 = 72 clips in April and May. The final result is 72.
</div>
</div>
<!-- User Section -->
<div style="margin-bottom: 20px;">
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">User</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Natalia sold three times as many items in June as she did in May. How many clips did Natalia sell altogether in these three months?
</div>
</div>
<!-- LLaDA-Instruct Section -->
<div>
<div style="font-weight: bold; color: #333; padding-bottom: 10px; font-size: 22px;">LLaDA-Instruct</div>
<div style="background-color: #f9f9f9; padding: 20px; border: 1px solid #ddd; border-radius: 8px; line-height: 1.6; font-size: 22px;">
Natalia sold clips to 48 friends in April. She sold half as many clips in May, so she sold 48/2 = 24 clips in May.
Natalia sold three times as many items in June as she did in May, so she sold 24 * 3 = 72 clips in June.
Altogether, Natalia sold 48 + 24 + 72 = 144 clips in these three months. The final result is 144.
</div>
</div>
</div>
</div>
</div>
</section>
<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title" style="font-family: 'Times New Roman', serif;">
BibTeX
</h2>
<pre><code>@misc{nie2025largelanguagediffusionmodels,
title={Large Language Diffusion Models},
author={Shen Nie and Fengqi Zhu and Zebin You and Xiaolu Zhang and Jingyang Ou and Jun Hu and Jun Zhou and Yankai Lin and Ji-Rong Wen and Chongxuan Li},
year={2025},
eprint={2502.09992},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2502.09992},
}</code></pre>
</div>
</section>
<section class="section" id="refer">
<div class="container is-max-desktop content">
<h2 class="title">References</h2>
<blockquote>
<p>
[1] Austin, J., Johnson, D. D., Ho, J., Tarlow, D., and
Van Den Berg, R. Structured denoising diffusion models
in discrete state-spaces. Advances in Neural Information
Processing Systems, 34:17981–17993, 2021a.
</p>
<p>
[2] Ou, J., Nie, S., Xue, K., Zhu, F., Sun, J., Li, Z.,
and Li, C. Your absorbing discrete diffusion secretly
models the conditional distributions of clean data.
arXiv preprint arXiv:2406.03736, 2024.
</p>
<p>
[3] Nie S, Zhu F, Du C, et al. Scaling up Masked Diffusion Models on Text[J]. arXiv preprint arXiv:2410.18514, 2024.
</p>
</blockquote>
</div>
</section>
</body>
</html>