FiSCo

groupfairnessllm's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 1 month ago

HR-MultiWOZ: A Task Oriented Dialogue (TOD) Dataset for HR LLM Agent

Paper • 2402.01018 • Published Feb 1, 2024 • 2

liked a dataset about 1 month ago

groupfairnessllm/tulu-3-sft-with-distraction

Viewer • Updated Oct 27 • 5.1k • 52 • 2

updated a dataset about 1 month ago

groupfairnessllm/tulu-3-sft-with-distraction

Viewer • Updated Oct 27 • 5.1k • 52 • 2

updated a collection about 1 month ago

Tulu3 with distraction mitigation data

Collection

LLM and LRM can be easily distracted by hidden instructions or irrelevant tasks. We curated SFT and DPO data that model can finetune to avoid distract • 5 items • Updated Oct 30 • 2

updated a dataset about 1 month ago

groupfairnessllm/tulu-3-preference-data-with-distraction

Viewer • Updated Oct 27 • 1.5k • 44

updated 5 datasets about 2 months ago

groupfairnessllm/tulu-3-sft-personas-code-with-distraction

Viewer • Updated Oct 21 • 1.7k • 26

groupfairnessllm/tulu-3-sft-personas-instruction-following-with-distraction

Viewer • Updated Oct 21 • 1.7k • 36

groupfairnessllm/tulu-3-sft-personas-math-with-distraction

Viewer • Updated Oct 21 • 1.7k • 23

groupfairnessllm/tulu-3-preference-personas-math-with-distraction

Viewer • Updated Oct 21 • 500 • 34

groupfairnessllm/tulu-3-preference-personas-instruction-following-with-distraction

Viewer • Updated Oct 21 • 500 • 24

updated a collection about 2 months ago

Tulu3 with distraction mitigation data

Collection

LLM and LRM can be easily distracted by hidden instructions or irrelevant tasks. We curated SFT and DPO data that model can finetune to avoid distract • 5 items • Updated Oct 30 • 2

upvoted a paper about 2 months ago

Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense

Paper • 2510.16259 • Published Oct 17 • 3

upvoted a collection about 2 months ago

Tulu3 with distraction mitigation data

Collection

LLM and LRM can be easily distracted by hidden instructions or irrelevant tasks. We curated SFT and DPO data that model can finetune to avoid distract • 5 items • Updated Oct 30 • 2

updated a collection about 2 months ago

Tulu3 with distraction mitigation data

Collection

LLM and LRM can be easily distracted by hidden instructions or irrelevant tasks. We curated SFT and DPO data that model can finetune to avoid distract • 5 items • Updated Oct 30 • 2

published 3 datasets about 2 months ago

groupfairnessllm/tulu-3-preference-data-with-distraction

Viewer • Updated Oct 27 • 1.5k • 44

groupfairnessllm/tulu-3-preference-personas-math-with-distraction

Viewer • Updated Oct 21 • 500 • 34

groupfairnessllm/tulu-3-preference-personas-instruction-following-with-distraction

Viewer • Updated Oct 21 • 500 • 24