996 citations · 1.6k across the 32 of their papers we have counts for
5 papers · 1 filter
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM
Zhilin Wang, Yi Dong, Jiaqi Zeng +8
Existing open-source helpfulness preference datasets do not specify what makes some responses more helpful and others less so. Models trained on these datasets can incidentally lea…
Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying
Adithya Renduchintala, Tugrul Konuk, Oleksii Kuchaiev
We introduce Tied-LoRA, a novel paradigm leveraging weight tying and selective training to enhance the parameter efficiency of Low-rank Adaptation (LoRA). Our exploration encompass…
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF
Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar +2
Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fin…
Leveraging Synthetic Targets for Machine Translation
Sarthak Mittal, Oleksii Hrinchuk, Oleksii Kuchaiev
In this work, we provide a recipe for training machine translation models in a limited resource setting by leveraging synthetic target data generated using a large pre-trained mode…
Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Boxin Wang, Wei Ping, Peng Xu +9
Large decoder-only language models (LMs) can be largely improved in terms of perplexity by retrieval (e.g., RETRO), but its impact on text generation quality and downstream task ac…