[NAACL 2025 Main Conference] PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
wujwyi
wuqiong1
AI & ML interests
None yet
Recent Activity
updated a dataset about 7 hours ago
wuqiong1/searchr1-silver-docs published a dataset about 7 hours ago
wuqiong1/searchr1-silver-docs updated a dataset about 8 hours ago
wuqiong1/searchr1-logsOrganizations
None yet
models 17
wuqiong1/new_corpus-single_loss_lambda0.5-keep_all_pass_filter
8B • Updated
wuqiong1/new_corpus-PreThink-AdvReb
8B • Updated
wuqiong1/3B-baseline-step206ckpt-Instruct-PreThink-SoftPen-AdvReb_ans
3B • Updated
wuqiong1/3B-Instruct-PreThink-SoftPen-AdvReb_ans
3B • Updated
wuqiong1/Llama3.2-3B-Instruct-PreThink-SoftPen-AdvReb_ans
4B • Updated
wuqiong1/AdvReb_all
8B • Updated
wuqiong1/PreThink-AdvReb_all
8B • Updated
wuqiong1/3B-new_corpus-PreThink-SoftPen-AdvReb_all
3B • Updated
wuqiong1/new_corpus-PreThink-SoftPen-AdvReb_all
8B • Updated
wuqiong1/PreThink-SoftPen-AdvReb_ans
8B • Updated