5 papers
Learning to Insert [PAUSE] Tokens for Better Reasoning
Eunki Kim, Sangryul Kim, James Thorne
To enhance reasoning capabilities, previous works have explored incorporating special-purpose tokens into the training process. These strategies strengthen the learning mechanism o…
On the Robustness of Reward Models for Language Model Alignment
Jiwoo Hong, Noah Lee, Eunki Kim +5
The Bradley-Terry (BT) model is widely practiced in reward modeling for reinforcement learning with human feedback (RLHF). Despite its effectiveness, reward models (RMs) trained wi…
Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions
Wan Ju Kang, Eunki Kim, Na Min An +4
Often, the needs and visual abilities differ between the annotator group and the end user group. Generating detailed diagram descriptions for blind and low-vision (BLV) users is on…
AlphaPO: Reward Shape Matters for LLM Alignment
Aman Gupta, Shao Tang, Qingquan Song +10
Reinforcement Learning with Human Feedback (RLHF) and its variants have made huge strides toward the effective alignment of large language models (LLMs) to follow instructions and…
I0T: Embedding Standardization Method Towards Zero Modality Gap
Na Min An, Eunki Kim, James Thorne +1
Contrastive Language-Image Pretraining (CLIP) enables zero-shot inference in downstream tasks such as image-text retrieval and classification. However, recent works extending CLIP…