15 papers
Large Databases Need Small, Open-Weight Language Models
Parker Glenn, Alfy Samuel
Language model systems built around proprietary APIs often operate on a token-based cost model. This becomes prohibitively expensive in the context of large databases, where LM-enh…
EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
Amin Banayeeanzade, Qingchuan Yang, Deqing Fu +6
High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for do…
Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs
Amin Banayeeanzade, Qingchuan Yang, Dhruv Tarsadiya +6
Diversity is essential for language-model applications ranging from creative generation to scientific discovery, yet modern LLMs often collapse into a narrow subset of plausible ou…
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Mengxuan Hu, Vivek V. Datla, Anoop Kumar +4
Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have impro…
Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization
Kushal Chawla, Chenyang Zhu, Pengshan Cai +9
Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically…
FB-RAG: Improving RAG with Forward and Backward Lookup
Kushal Chawla, Alfy Samuel, Anoop Kumar +1
Traditional Retrieval-Augmented Generation (RAG) struggles with complex queries that lack strong signals to retrieve the most relevant context, forcing a trade-off between choosing…