Abstract2Appendix: Academic Reviews Enhance LLM Long-Context Capabilities
Paper
•
2411.05232
•
Published
Research to the People
non-profit
AI & ML interests
Cancer and Rare Disease.
Recent Activity
View all activity
RTTP's activity
alexshengzhiliÂ
authored
a
paper
about 1 month ago
alexshengzhiliÂ
posted
an
update
about 1 month ago
Post
1125
We’re excited to release Abstract2Appendix v1 10K , a high-quality dataset crafted to enhance the long-context capabilities of Large Language Models (LLMs). This dataset combines thousands of peer reviews from NeurIPS 2023, EMNLP 2023, TMLR, and ICLR 2023, making it a treasure trove of detailed feedback, critical reasoning, and structured academic insights. Our experiments showed that this dataset increased long context ability of phi-3 models!
🌟 Key Highlights:
• Expert Reviews: Aggregated from 3–6 reviews per paper, capturing the most insightful and constructive content.
• Rich Metadata: we have aggregated the reviews, and also included full parsed paper
• LLM Ready: Perfect for fine-tuning (We did dpo and sft)
🎯 Use Cases:
• Fine-tuning models with Direct Preference Optimization (DPO) and Supervised Fine-Tuning (SFT).
• Benchmarking zero-shot and long-context comprehension capabilities.
đź”— Explore the dataset: alexshengzhili/Abstract2Appendix_v1_10k
This dataset is based on the methodology described in our recent paper, “Abstract2Appendix: Academic Reviews Enhance LLM Long-Context Capabilities”. Check it out for more details! https://arxiv.org/abs/2411.05232
🌟 Key Highlights:
• Expert Reviews: Aggregated from 3–6 reviews per paper, capturing the most insightful and constructive content.
• Rich Metadata: we have aggregated the reviews, and also included full parsed paper
• LLM Ready: Perfect for fine-tuning (We did dpo and sft)
🎯 Use Cases:
• Fine-tuning models with Direct Preference Optimization (DPO) and Supervised Fine-Tuning (SFT).
• Benchmarking zero-shot and long-context comprehension capabilities.
đź”— Explore the dataset: alexshengzhili/Abstract2Appendix_v1_10k
This dataset is based on the methodology described in our recent paper, “Abstract2Appendix: Academic Reviews Enhance LLM Long-Context Capabilities”. Check it out for more details! https://arxiv.org/abs/2411.05232
hayuhÂ
updated
a
Space
6 months ago
dcgenomicsÂ
updated
a
model
6 months ago
dontjandraÂ
updated
a
model
6 months ago
alexshengzhiliÂ
posted
an
update
10 months ago
Post
After the Supervised Fine-Tuning (SFT) phase, we observed a notable degradation in the instruction-following capabilities of the LLaVA Multi-Modal Large Language Model (MM-LLM). To address this issue, we introduced a 6K-entry VQA preference dataset and employed Direct Preference Optimization (DPO), alongside testing other algorithms such as Rejection Sampling and SteerLM, to enhance instruction-following proficiency. Our methodology not only fully restored the language following capabilities of LLaVa on the MT-Bench but also outperformed LLaVA-RLHF and Vicuna. Additionally, our approach extended to visual VQA tasks, as demonstrated by significant performance improvements on MM-Vet and LLaVa-Bench. An interesting observation was that, compared to models using distilled SFT, our method showed substantial out-of-distribution improvements.
https://arxiv.org/abs/2402.10884
Model available
alexshengzhili/llava-v1.5-13b-dpo
GitHub:
https://github.com/findalexli/mllm-dpo/edit/main/README.MD
alexshengzhiliÂ
authored
2
papers
10 months ago