Neurosymbolic LoRA: Why and When to Tune Weights vs. Rewrite Prompts
Large language models (LLMs) can be adapted either through numerical updates that alter model parameters or symbolic manipulations that work on discrete prompts or logical constraints. While numerical fine-tuning excels at injecting new factual knowledge, symbolic updates offer flexible control of style and alignment without retraining. We introduce a neurosymbolic LoRA framework that dynamically combines these two complementary strategies. Specifically, we present a unified monitoring signal and a reward-based classifier to decide when to employ LoRA for deeper factual reconstruction and when to apply TextGrad for token-level edits. Our approach remains memory-efficient by offloading the symbolic transformations to an external LLM only when needed. Additionally, the refined prompts produced during symbolic editing serve as high-quality, reusable training data, an important benefit in data-scarce domains like mathematical reasoning. Extensive experiments across multiple LLM backbones show that neurosymbolic LoRA consistently outperforms purely numerical or purely symbolic baselines, demonstrating superior adaptability and improved performance. Our findings highlight the value of interleaving numerical and symbolic updates to unlock a new level of versatility in language model fine-tuning.
Code (0)
등록된 구현이 없습니다.
Tasks
Mathematical ReasoningSimilar Papers 제목 키워드 기반
VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigation
Rapid adaptation in unseen environments is essential for scalable real-world autonomy, yet existing approaches rely on exhaustive exploration or rigid navigation policies that fail to generalize. We present VLN-Zero, a t…
Vision-Language NavigationRobot NavigationIntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models
Fine-tuning pre-trained diffusion models under limited budgets has gained great success. In particular, the recent advances that directly fine-tune the quantized weights using Low-rank Adaptation (LoRA) further reduces t…
parameter-efficient fine-tuningQuantizationCompiling Rewrite Rules to Finite-State Transducers with the Worsening Trick
Finite-state transducers (FSTs) are essential for modeling string rewriting in computational linguistics and natural language processing (NLP), particularly for phonological and morphological rewrite rules. Compiling gen…
Model merging with SVD to tie the Knots
Recent model merging methods demonstrate that the parameters of fully-finetuned models specializing in distinct tasks can be combined into one model capable of solving all tasks without retraining. Yet, this success does…
modelNeurosymbolic Reinforcement Learning with Formally Verified Exploration
We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces. A key challenge for provably safe deep RL is that repeatedly verifying neura…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Exploration