Fine-Tuning LLMs to Generate Economical and Reliable Actions for the Power Grid

• URL: http://arxiv.org/abs/2602.15350v1
• Date: Tue, 17 Feb 2026 04:33:02 GMT
• Title: Fine-Tuning LLMs to Generate Economical and Reliable Actions for the Power Grid
• Abstract summary: Public Safety Power Shutoffs (PSPS) force rapid topology changes that can render standard operating points infeasible.<n>We present a verifiable, multi-stage adaptation pipeline that fine-tunes an instruction-tuned large language model (LLM) to generate emphopen-only corrective switching plans.
• Score: 4.826124200824742
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Public Safety Power Shutoffs (PSPS) force rapid topology changes that can render standard operating points infeasible, requiring operators to quickly identify corrective transmission switching actions that reduce load shedding while maintaining acceptable voltage behavior. We present a verifiable, multi-stage adaptation pipeline that fine-tunes an instruction-tuned large language model (LLM) to generate \emph{open-only} corrective switching plans from compact PSPS scenario summaries under an explicit switching budget. First, supervised fine-tuning distills a DC-OPF MILP oracle into a constrained action grammar that enables reliable parsing and feasibility checks. Second, direct preference optimization refines the policy using AC-evaluated preference pairs ranked by a voltage-penalty metric, injecting voltage-awareness beyond DC imitation. Finally, best-of-$N$ selection provides an inference-time addition by choosing the best feasible candidate under the target metric. On IEEE 118-bus PSPS scenarios, fine-tuning substantially improves DC objective values versus zero-shot generation, reduces AC power-flow failure from 50\% to single digits, and improves voltage-penalty outcomes on the common-success set. Code and data-generation scripts are released to support reproducibility.

Related papers

• LiFT: Local Search via Linear Programming for Overfitting-Controlled Transformers [0.16866396683295748]
  This paper proposes a Linear Programming (LP)-based local search framework for fine-tuning transformer models with explicit control against overfitting.<n>Experiments on GPT-2 Small on WikiText-2 demonstrate that LiFT enables effective adaptation through selective tuning of transformer blocks and regularization parameters.
  arXiv  Detail & Related papers  (2026-06-15T05:42:59Z)
• ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric Constraints [26.309376587678354]
  We propose Asymmetric Constrained Preference Optimization (ACPO)<n>ACPO applies dynamic, target-oriented scaling to preference optimization.<n>We show that ACPO effectively reverses the chosen-reward degradation of standard DPO.
  arXiv  Detail & Related papers  (2026-03-23T16:26:11Z)
• Diffusion Controller: Framework, Algorithms and Parameterization [54.82539154511621]
  We present a unified control-theoretic view that casts reverse diffusion sampling as state-only control within (generalized) linearly-solvable Markov Decision Processes.<n>Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost.<n>Experiments on Stable Diffusion v1.4 show consistent gains in preference-alignment win rates and improved quality-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-03-07T01:49:59Z)
• MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation [12.481603155570037]
  We propose textbfMMLoP (textbfMulti-textbfModal textbfLow-Rank textbfPrompting), a framework that achieves deep multi-modal prompting with only textbf11.5K trainable parameters.
  arXiv  Detail & Related papers  (2026-02-24T22:00:34Z)
• LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs [61.06744611795341]
  Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging.<n>We propose texttttextbfLATA (Laplacian-Assisted Transductive Adaptation), a textittraining- and label-free refinement.<n>texttttextbfLATA sharpens zero-shot predictions without compromising exchangeability.
  arXiv  Detail & Related papers  (2026-02-19T16:45:38Z)
• HPTune: Hierarchical Proactive Tuning for Collision-Free Model Predictive Control [55.015741360766945]
  We propose a hierarchical proactive tuning (HPTune) framework that combines both a fast-level tuning and a slow-level tuning.<n>We integrate HPTune with the Doppler LiDAR that provides obstacle velocities apart from position-only measurements for enhanced motion predictions.<n>It is found that HPTune enables situation-tailored motion planning by formulating a safe, agile collision avoidance strategy.
  arXiv  Detail & Related papers  (2026-01-29T07:15:39Z)
• An Adaptive Purification Controller for Quantum Networks: Dynamic Protocol Selection and Multipartite Distillation [10.706268477180858]
  We propose an Adaptive Purification Controller (APC) that automatically optimize the entanglement distillation sequence to maximize the goodput.<n>We show that our approach mitigates the "fidelity cliffs" inherent in static protocols and reduces resource wastage in high-noise regimes.<n>We extend the controller to heterogeneous scenarios, and evaluate it for both multipartite GHZ state generation and continuous-variable systems.
  arXiv  Detail & Related papers  (2026-01-26T10:56:37Z)
• GateRA: Token-Aware Modulation for Parameter-Efficient Fine-Tuning [51.79350934271497]
  GateRA is a unified framework that introduces token-aware modulation to dynamically adjust the strength of PEFT updates.<n>By incorporating adaptive gating into standard PEFT branches, GateRA enables selective, token-level adaptation.<n> Experiments on multiple commonsense reasoning benchmarks demonstrate that GateRA consistently outperforms or matches prior PEFT methods.
  arXiv  Detail & Related papers  (2025-11-15T17:55:47Z)
• Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits [8.041642853381909]
  We introduce Alignment-Aware Probe Pruning (AAPP), a dynamic structured pruning method that adaptively preserves alignment-relevant circuits during inference.<n>Experiments on LLaMA 2-7B, Qwen2.5-14B-Instruct, and Gemma-3-12B-IT show AAPP improves refusal rates by 50% at matched compute.
  arXiv  Detail & Related papers  (2025-11-09T16:51:45Z)
• PASS-Enhanced MEC: Joint Optimization of Task Offloading and Uplink PASS Beamforming [67.78883135636657]
  pinching-antenna system (PASS)-enhanced mobile edge computing (MEC) architecture is investigated.<n>PASS establishes short-distance line-of-sight (LoS) links while effectively mitigating the significant path loss and potential signal blockage.<n>We formulate a network latency minimization problem to joint optimize uplink PASS beamforming and task offloading.
  arXiv  Detail & Related papers  (2025-10-27T03:04:46Z)
• REFA: Reference Free Alignment for multi-preference optimization [27.079664155329535]
  We introduce REFA, a new alignment framework that proposes probabilistic control on a structural token that controls termination.<n> REFA achieves a 60.29% win rate and a 52.17% length-controlled win rate on AlpacaEval2 with Llama-3-8B-Instruct.
  arXiv  Detail & Related papers  (2024-12-20T22:25:23Z)
• Learning Model Predictive Control Parameters via Bayesian Optimization for Battery Fast Charging [0.0]
  tuning parameters in model predictive control (MPC) presents significant challenges, particularly when there is a notable discrepancy between the controller's predictions and the behavior of the closed-loop plant. We apply Bayesian optimization for efficient learning of unknown model parameters and parameterized constraint backoff terms, aiming to improve closed-loop performance of battery fast charging.
  arXiv  Detail & Related papers  (2024-04-09T08:49:41Z)
• Approximated Prompt Tuning for Vision-Language Pre-trained Models [54.326232586461614]
  In vision-language pre-trained models, prompt tuning often requires a large number of learnable tokens to bridge the gap between the pre-training and downstream tasks. We propose a novel Approximated Prompt Tuning (APT) approach towards efficient VL transfer learning.
  arXiv  Detail & Related papers  (2023-06-27T05:43:47Z)
• Scalable Optimal Design of Incremental Volt/VAR Control using Deep Neural Networks [2.018732483255139]
  We propose a scalable solution by reformulating Optimal Rule Design (ORD) as training a deep neural network (DNN) We put forth a scalable solution by reformulating ORD as training a deep neural network (DNN) Analytical findings and numerical tests corroborate that the proposed ORD solution can be neatly adapted to single/multi-phase feeders.
  arXiv  Detail & Related papers  (2023-01-04T04:19:12Z)
• Effective Pre-Training Objectives for Transformer-based Autoencoders [97.99741848756302]
  We study trade-offs between efficiency, cost and accuracy of Transformer encoders. We combine features of common objectives and create new effective pre-training approaches.
  arXiv  Detail & Related papers  (2022-10-24T18:39:44Z)
• Data-Driven Stochastic AC-OPF using Gaussian Processes [54.94701604030199]
  Integrating a significant amount of renewables into a power grid is probably the most a way to reduce carbon emissions from power grids slow down climate change. This paper presents an alternative data-driven approach based on the AC power flow equations that can incorporate uncertainty inputs. The GP approach learns a simple yet non-constrained data-driven approach to close this gap to the AC power flow equations.
  arXiv  Detail & Related papers  (2022-07-21T23:02:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.