CORTEXA
← Browse
arxivcs.LGcs.AIcs.CL2026-07-02

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie, Stuart Shieber, Yuntian Deng

Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large language model APIs at the cost of locality, reproducibility, and price. We propose fuzzy-function programming: compiling such a function from a natural-language specification into a compact, locally-executable neural artifact. We instantiate this paradigm with Program-as-Weights (PAW), in which a 4B compiler trained on FuzzyBench, a 10M-example dataset we release, emits parameter-efficient adapters for a frozen, lightweight interpreter. A 0.6B Qwen3 interpreter executing PAW programs matches the performance of direct prompting of Qwen3-32B, while using roughly one fiftieth of the inference memory and running at 30 tokens/s on a MacBook M3. PAW reframes the foundation model from a per-input problem solver into a tool builder: invoked once per function definition, it produces a small reusable artifact whose subsequent calls per function application are cheap and offline.

View free PDFSource page

Related papers

arxivcs.CLcs.AIcs.LG2026-07-08

Co-LMLM: Continuous-Query Limited Memory Language Models

Yair Feldman, Linxi Zhao, Nathan Godey, Dongyoung Go, Yilun Hua, Kilian Q. Weinberger, et al.

Limited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rather than memorizing it in their weights. During generation, the model then fetches knowledge from the KB as needed. This recently introduced paradigm provides mult…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-07-15

Data-Efficient Adaptation of LLMs via Attention Head Reweighting

Tuomas Oikarinen, Zixiao Chen, Charlotte Siska, Tsui-Wei Weng, Chandan Singh, Jianfeng Gao

Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large language models (LLMs) have demonstrated some capabilities for data-efficient learning, especially through parameter-efficient adaptation methods, but continue to…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-07-04

Punching Above Their Weight: Classification-Head Fine-Tuning of Tiny Language Models (TLMs) for Verifiable Multiple-Choice Tasks

Bhavesh Sood, Jaromir Savelka

We define Tiny Language Models (TLMs) as models below roughly 3B parameters that fit on mainstream consumer devices. We study how to adapt them for and use them on verifiable multiple-choice tasks. We compare three LoRA-based fine-tuning paradigms (label generation, gold only, an…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-07-06

Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing

Babak Barazandeh, Subhabrata Majumdar, Vinay Prithyani, George Michailidis

Large Language Models (LLMs) and high-dimensional perception networks increasingly rely on parameter-efficient fine-tuning (PEFT) to adapt to diverse operational contexts. However, standard methods like LoRA are structurally limited by a monolithic bottleneck, making them highly…

View free PDFSource page
arxivcs.CLcs.AIcs.LG2026-07-07

Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design

Alexander Rombach, Chantale Lauer, Nijat Mehdiyev

Large language models (LLMs) can generate BPMN process models from natural-language descriptions, yet supervised fine-tuning (SFT) limits their output quality to the patterns present in the training data. Reinforcement learning (RL) can optimize beyond this ceiling using external…

View free PDFSource page