Changes
On December 16, 2024 at 6:38:14 PM UTC, admin:
-
Changed value of field
doi_status
toTrue
in Fine-tuning Language Models with Advantage-Induced Policy Alignment -
Changed value of field
doi_date_published
to2024-12-16
in Fine-tuning Language Models with Advantage-Induced Policy Alignment -
Added resource Original Metadata to Fine-tuning Language Models with Advantage-Induced Policy Alignment
f | 1 | { | f | 1 | { |
2 | "access_rights": "", | 2 | "access_rights": "", | ||
3 | "author": "Banghua Zhu", | 3 | "author": "Banghua Zhu", | ||
4 | "author_email": "", | 4 | "author_email": "", | ||
5 | "citation": [], | 5 | "citation": [], | ||
6 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | 6 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | ||
7 | "defined_in": "", | 7 | "defined_in": "", | ||
8 | "doi": "10.57702/3oqqdleq", | 8 | "doi": "10.57702/3oqqdleq", | ||
n | 9 | "doi_date_published": null, | n | 9 | "doi_date_published": "2024-12-16", |
10 | "doi_publisher": "TIB", | 10 | "doi_publisher": "TIB", | ||
n | 11 | "doi_status": false, | n | 11 | "doi_status": true, |
12 | "domain": "https://service.tib.eu/ldmservice", | 12 | "domain": "https://service.tib.eu/ldmservice", | ||
13 | "extra_authors": [ | 13 | "extra_authors": [ | ||
14 | { | 14 | { | ||
15 | "extra_author": "Hiteshi Sharma", | 15 | "extra_author": "Hiteshi Sharma", | ||
16 | "orcid": "" | 16 | "orcid": "" | ||
17 | }, | 17 | }, | ||
18 | { | 18 | { | ||
19 | "extra_author": "Felipe Vieira Frujeri", | 19 | "extra_author": "Felipe Vieira Frujeri", | ||
20 | "orcid": "" | 20 | "orcid": "" | ||
21 | }, | 21 | }, | ||
22 | { | 22 | { | ||
23 | "extra_author": "Shi Dong", | 23 | "extra_author": "Shi Dong", | ||
24 | "orcid": "" | 24 | "orcid": "" | ||
25 | }, | 25 | }, | ||
26 | { | 26 | { | ||
27 | "extra_author": "Michael I. Jordan", | 27 | "extra_author": "Michael I. Jordan", | ||
28 | "orcid": "" | 28 | "orcid": "" | ||
29 | }, | 29 | }, | ||
30 | { | 30 | { | ||
31 | "extra_author": "Jiantao Jiao", | 31 | "extra_author": "Jiantao Jiao", | ||
32 | "orcid": "" | 32 | "orcid": "" | ||
33 | } | 33 | } | ||
34 | ], | 34 | ], | ||
35 | "groups": [ | 35 | "groups": [ | ||
36 | { | 36 | { | ||
37 | "description": "", | 37 | "description": "", | ||
38 | "display_name": "Language Models", | 38 | "display_name": "Language Models", | ||
39 | "id": "34093697-48eb-4485-bcca-1284a763a07e", | 39 | "id": "34093697-48eb-4485-bcca-1284a763a07e", | ||
40 | "image_display_url": "", | 40 | "image_display_url": "", | ||
41 | "name": "language-models", | 41 | "name": "language-models", | ||
42 | "title": "Language Models" | 42 | "title": "Language Models" | ||
43 | }, | 43 | }, | ||
44 | { | 44 | { | ||
45 | "description": "", | 45 | "description": "", | ||
46 | "display_name": "Reinforcement Learning", | 46 | "display_name": "Reinforcement Learning", | ||
47 | "id": "5f9e20df-0af0-4b7e-9637-e244d4a99379", | 47 | "id": "5f9e20df-0af0-4b7e-9637-e244d4a99379", | ||
48 | "image_display_url": "", | 48 | "image_display_url": "", | ||
49 | "name": "reinforcement-learning", | 49 | "name": "reinforcement-learning", | ||
50 | "title": "Reinforcement Learning" | 50 | "title": "Reinforcement Learning" | ||
51 | } | 51 | } | ||
52 | ], | 52 | ], | ||
53 | "id": "0d29d556-b621-490f-9bbc-65bec9969c32", | 53 | "id": "0d29d556-b621-490f-9bbc-65bec9969c32", | ||
54 | "isopen": false, | 54 | "isopen": false, | ||
55 | "landing_page": | 55 | "landing_page": | ||
56 | "https://huggingface.co/datasets/lvwerra/stack-exchange-paired", | 56 | "https://huggingface.co/datasets/lvwerra/stack-exchange-paired", | ||
57 | "license_title": null, | 57 | "license_title": null, | ||
58 | "link_orkg": "", | 58 | "link_orkg": "", | ||
59 | "metadata_created": "2024-12-16T18:38:13.093751", | 59 | "metadata_created": "2024-12-16T18:38:13.093751", | ||
n | 60 | "metadata_modified": "2024-12-16T18:38:13.093758", | n | 60 | "metadata_modified": "2024-12-16T18:38:13.601197", |
61 | "name": | 61 | "name": | ||
62 | "fine-tuning-language-models-with-advantage-induced-policy-alignment", | 62 | "fine-tuning-language-models-with-advantage-induced-policy-alignment", | ||
63 | "notes": "The dataset used in the paper is the Anthropic Helpfulness | 63 | "notes": "The dataset used in the paper is the Anthropic Helpfulness | ||
64 | and Harmlessness dataset and the StackExchange dataset.", | 64 | and Harmlessness dataset and the StackExchange dataset.", | ||
n | 65 | "num_resources": 0, | n | 65 | "num_resources": 1, |
66 | "num_tags": 3, | 66 | "num_tags": 3, | ||
67 | "organization": { | 67 | "organization": { | ||
68 | "approval_status": "approved", | 68 | "approval_status": "approved", | ||
69 | "created": "2024-11-25T12:11:38.292601", | 69 | "created": "2024-11-25T12:11:38.292601", | ||
70 | "description": "", | 70 | "description": "", | ||
71 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 71 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
72 | "image_url": "", | 72 | "image_url": "", | ||
73 | "is_organization": true, | 73 | "is_organization": true, | ||
74 | "name": "no-organization", | 74 | "name": "no-organization", | ||
75 | "state": "active", | 75 | "state": "active", | ||
76 | "title": "No Organization", | 76 | "title": "No Organization", | ||
77 | "type": "organization" | 77 | "type": "organization" | ||
78 | }, | 78 | }, | ||
79 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 79 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
80 | "private": false, | 80 | "private": false, | ||
81 | "relationships_as_object": [], | 81 | "relationships_as_object": [], | ||
82 | "relationships_as_subject": [], | 82 | "relationships_as_subject": [], | ||
t | 83 | "resources": [], | t | 83 | "resources": [ |
84 | { | ||||
85 | "cache_last_updated": null, | ||||
86 | "cache_url": null, | ||||
87 | "created": "2024-12-16T18:25:36", | ||||
88 | "data": [ | ||||
89 | "dcterms:title", | ||||
90 | "dcterms:accessRights", | ||||
91 | "dcterms:creator", | ||||
92 | "dcterms:description", | ||||
93 | "dcterms:issued", | ||||
94 | "dcterms:language", | ||||
95 | "dcterms:identifier", | ||||
96 | "dcat:theme", | ||||
97 | "dcterms:type", | ||||
98 | "dcat:keyword", | ||||
99 | "dcat:landingPage", | ||||
100 | "dcterms:hasVersion", | ||||
101 | "dcterms:format", | ||||
102 | "mls:task" | ||||
103 | ], | ||||
104 | "description": "The json representation of the dataset with its | ||||
105 | distributions based on DCAT.", | ||||
106 | "format": "JSON", | ||||
107 | "hash": "", | ||||
108 | "id": "ab41a73b-8892-41ae-9ed5-0d1c3901f088", | ||||
109 | "last_modified": "2024-12-16T18:38:13.593403", | ||||
110 | "metadata_modified": "2024-12-16T18:38:13.604188", | ||||
111 | "mimetype": "application/json", | ||||
112 | "mimetype_inner": null, | ||||
113 | "name": "Original Metadata", | ||||
114 | "package_id": "0d29d556-b621-490f-9bbc-65bec9969c32", | ||||
115 | "position": 0, | ||||
116 | "resource_type": null, | ||||
117 | "size": 841, | ||||
118 | "state": "active", | ||||
119 | "url": | ||||
120 | resource/ab41a73b-8892-41ae-9ed5-0d1c3901f088/download/metadata.json", | ||||
121 | "url_type": "upload" | ||||
122 | } | ||||
123 | ], | ||||
84 | "services_used_list": "", | 124 | "services_used_list": "", | ||
85 | "state": "active", | 125 | "state": "active", | ||
86 | "tags": [ | 126 | "tags": [ | ||
87 | { | 127 | { | ||
88 | "display_name": "Advantage-Induced Policy Alignment", | 128 | "display_name": "Advantage-Induced Policy Alignment", | ||
89 | "id": "2faa412a-317d-42f7-92af-fecd3a504f86", | 129 | "id": "2faa412a-317d-42f7-92af-fecd3a504f86", | ||
90 | "name": "Advantage-Induced Policy Alignment", | 130 | "name": "Advantage-Induced Policy Alignment", | ||
91 | "state": "active", | 131 | "state": "active", | ||
92 | "vocabulary_id": null | 132 | "vocabulary_id": null | ||
93 | }, | 133 | }, | ||
94 | { | 134 | { | ||
95 | "display_name": "Language Models", | 135 | "display_name": "Language Models", | ||
96 | "id": "3c8ccbd5-9585-4599-8612-76c0221af944", | 136 | "id": "3c8ccbd5-9585-4599-8612-76c0221af944", | ||
97 | "name": "Language Models", | 137 | "name": "Language Models", | ||
98 | "state": "active", | 138 | "state": "active", | ||
99 | "vocabulary_id": null | 139 | "vocabulary_id": null | ||
100 | }, | 140 | }, | ||
101 | { | 141 | { | ||
102 | "display_name": "Reinforcement Learning", | 142 | "display_name": "Reinforcement Learning", | ||
103 | "id": "0bd14238-9c5d-4905-8165-c7e5a0c0884c", | 143 | "id": "0bd14238-9c5d-4905-8165-c7e5a0c0884c", | ||
104 | "name": "Reinforcement Learning", | 144 | "name": "Reinforcement Learning", | ||
105 | "state": "active", | 145 | "state": "active", | ||
106 | "vocabulary_id": null | 146 | "vocabulary_id": null | ||
107 | } | 147 | } | ||
108 | ], | 148 | ], | ||
109 | "title": "Fine-tuning Language Models with Advantage-Induced Policy | 149 | "title": "Fine-tuning Language Models with Advantage-Induced Policy | ||
110 | Alignment", | 150 | Alignment", | ||
111 | "type": "dataset", | 151 | "type": "dataset", | ||
112 | "version": "" | 152 | "version": "" | ||
113 | } | 153 | } |