The paper proposes a two‑stage framework for expanding and refining a set of prompts for language models under a limited evaluation budget. In the first stage, it generates a finite candidate set of prompts represented by moderate‑dimensional vectors. The second stage builds a surrogate model of prompt scores and sequentially selects prompts for evaluation, proving consistency of this procedure and introducing a refinement step that searches beyond the initial candidates. Numerical experiments show the method outperforms baseline prompt selection, especially when evaluation calls are constrained.
By Haoting Zhang, Jinghai He, Rhonda Righter, Zeyu Zheng
CHAI for LLMs is a framework that improves large language models’ performance on code‑mixed translation tasks by using LLMs as annotators to create preference data, applying reinforcement learning from AI feedback, incorporating LLM‑generated domain knowledge for iterative refinement, and evaluating on real‑world datasets. The approach yields a 68.45% average win rate over state‑of‑the‑art open‑source models in human‑adjudicated tests. It demonstrates a scalable method to enhance code‑mixed language understanding in open‑source LLMs.
By Wenbo Zhang, Aditya Majumdar, Asif Ekbal, Amulya Yadav
arXiv:2610.32982v1 Announce Type: new
Abstract: This article argues that instruction-fine-tuned language models should be understood as implementing a genre, what is proposed as the instructional-con...
By James E. Dobson
arXiv:2607. 28657v1 Announce Type: new Abstract: Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users.
By Oliver Savolainen, Emanuele Bastianelli, Hosein Azarbonyad
arXiv:2610.35029v1 Announce Type: new
Abstract: Synthetic data has become a common resource for training language models, and this trend has spilled over into research on developmentally plausible la...
By Bastian Bunzeck, Francesca Padovani
GFlowPO introduces a probabilistic framework for optimizing language model prompts by treating prompt search as posterior inference over latent prompts, regularized by a meta-prompted reference-LM prior. The method first fine‑tunes a lightweight prompt‑LM using an off‑policy Generative Flow Network objective that reuses past prompt evaluations for sample‑efficient exploration. It then applies a training‑free Dynamic Memory Update to refine the meta‑prompt with diverse and top‑performing prompts, leading to consistent improvements over recent discrete prompt optimization baselines on few‑shot classification, instruction induction, and question‑answering tasks.
By Junmo Cho, Suhan Kim, Sangjune An, Minsu Kim, Dong Bok Lee, Heejun Lee, Sung Ju Hwang, Hae Beom Lee