7 papers · 1 filter
ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation
Yiming Xu, Yuan Yuan, Vijay Viswanathan +1
Text clustering is a fundamental task in natural language processing, yet traditional clustering algorithms with pre-trained embeddings often struggle in domain-specific contexts w…
Checklists Are Better Than Reward Models For Aligning Language Models
Vijay Viswanathan, Yanchao Sun, Shuang Ma +4
Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "help…
Evaluating Language Models as Synthetic Data Generators
Seungone Kim, Juyoung Suk, Xiang Yue +7
Given the increasing use of synthetic data in language model (LM) post-training, an LM's ability to generate high-quality data has become nearly as crucial as its ability to solve…
Synthetic Multimodal Question Generation
Ian Wu, Sravan Jayanthi, Vijay Viswanathan +4
Multimodal Retrieval Augmented Generation (MMRAG) is a powerful approach to question-answering over multimodal documents. A key challenge with evaluating MMRAG is the paucity of hi…
SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning
Chenyang Zhao, Xueying Jia, Vijay Viswanathan +2
Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. However, prompting often leads models to make predic…
Training Task Experts through Retrieval Based Distillation
Jiaxin Ge, Xueying Jia, Vijay Viswanathan +2
One of the most reliable ways to create deployable models for specialized tasks is to obtain an adequate amount of high-quality task-specific data. However, for specialized tasks,…