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
GrammarRL introduces a label‑free reinforcement learning approach that adapts language models to grammar constraints without annotated data. It optimizes two self‑supervised rewards—direct and reverse—using a Reinforce Leave‑One‑Out objective over grammar‑constrained rollouts, and regularizes toward a frozen base model. Experiments on sign‑language gloss translation, hierarchical text classification, and named entity recognition with Llama models show consistent gains over constrained greedy decoding and competitive performance to beam search while keeping inference cost low.
By Gabriele Tuccio, Antonino Furnari, Aldo Gangemi, Misael Mongiov\`{\i}
arXiv:2605. 27642v2 Announce Type: replace-cross Abstract: Soft prompting, also known as continuous prompting, is a parameter-efficient method for tuning LLMs to specific tasks.
By Pitipat Kongsomjit, Suryansh Goyal, Jacob Whitehill
We introduce Dango, a 1. 8B-parameter large language model designed for controlled studies of L1-to-L2 (Japanese-to-English) transfer in second language acquisition (SLA).
arXiv:2407. 03884v4 Announce Type: replace-cross Abstract: Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks.
By Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, Yuqian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, Deyi Xiong
arXiv:2605. 18476v2 Announce Type: replace-cross Abstract: Coding and computation remain major bottlenecks in Markov chain Monte Carlo (MCMC) workflows, especially as modern sampling algorithms have become increasingly complex and existing probabilistic programming systems remain limited in model support, extensibility, and composability.
By Jungang Zou, Alex Ziyu Jiang, Qixuan Chen
The study investigates how language models acquire in-context learning (ICL) by distinguishing between copying a nearby demonstration and integrating information across a prompt. Across 17 models, roughly one-third default to copied answers, a few are undecided, and the remainder favor rule-consistent answers that yield higher accuracy and are guided by the requested value rather than the nearest conflicting example. Analyses show that models prioritize task-relevant prompt tokens before accuracy surpasses chance, and that synthetic or fine-tuned training can shift models toward compositional responses or improve accuracy when prompts reassign label meanings.
By Minglai Yang, Xinyu Guo, Renxiong Wang, Sunjie Hou, Daniel Yue Zhang, Yunzhong He