Weave of Formal Thought

• URL: http://arxiv.org/abs/2606.25987v1
• Date: Wed, 24 Jun 2026 15:58:11 GMT
• Title: Weave of Formal Thought
• Abstract summary: We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
• Score: 51.56484100374058
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) attain remarkable surface fluency on code, yet they neither formally guarantee the syntactic validity of their output nor leverage the hierarchical structure defining the target language. While existing constrained-decoding frameworks address the former, they operate under rigid assumptions that preclude critical lexical mechanisms -- including context-sensitive lexing, maximal-munch tokenization, and keyword extraction -- and only approximate vocabulary masking, sacrificing completeness. For the latter, code LLMs typically inject grammatical structure via predetermined policies rather than learning which structural information to expose. In this work, we introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations. First, we present a formal engine and constrained decoder that is sound and complete with respect to the full Tree-sitter specification. By augmenting generalized LR (GLR) parsing with a speculative-lexing construction that maintains concurrent lexer-state hypotheses synchronized with a GLR graph-structured stack, our decoder admits every subword token extending to a valid program prefix and rejects all others. Second, we present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation. Utilizing the reweighted wake-sleep (RWS) algorithm to optimize the importance-weighted evidence lower bound (IW-ELBO) of the surface text, the model learns to selectively retain formal derivations as an adaptive structural scratchpad. For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline, demonstrating that discretionary latent syntax recovers critical structural information that flat autoregressive training discards.

Related papers

• Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning [0.0]
  Sentence Splitter is a self-supervised framework built upon a T5-based encoder--decoder architecture.<n>The proposed method identifies the semantic boundary between a prefix (head) and its factual completion (tail)<n> Experiments on both structured and naturally occurring text demonstrate that the proposed splitter generalizes beyond synthetic templates.
  arXiv  Detail & Related papers  (2026-07-22T07:30:39Z)
• Empirical Study for Structured Output Control in LLMs for Software Engineering [13.096361151631427]
  A semantically correct output that violates the expected format is, from the consuming system's perspective, indistinguishable from a wrong answer.<n>We present a systematic evaluation of structural reliability across four representative SE tasks.<n>We highlight the need for approaches that jointly ensure structural fidelity and semantic correctness in LLM-driven errors.
  arXiv  Detail & Related papers  (2026-06-08T12:13:58Z)
• $\mathcal{S}^2$IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction [51.165432266846096]
  syntactic structure information is underutilized in the generative paradigm of large language models (LLMs)<n>S2IT progressively integrates syntactic structure knowledge into LLMs through a multi-step tuning process.<n> Experiments demonstrate that S2IT significantly improves state-of-the-art performance across multiple datasets.
  arXiv  Detail & Related papers  (2026-04-25T13:24:29Z)
• Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge [50.009682083079205]
  We investigate whether contextual recall emerges from pretraining alone.<n>We show that finetuning on tasks requiring implicit inference, distinct from the ICL evaluation, triggers the emergence of contextual recall.<n>For mechanistic insight, we derive a construction for an attention-only transformer that replicates the transition from factual to contextual recall.
  arXiv  Detail & Related papers  (2026-03-21T22:46:55Z)
• Tokenization, Fusion and Decoupling: Bridging the Granularity Mismatch Between Large Language Models and Knowledge Graphs [20.946228883628013]
  We propose KGT, a novel framework that uses dedicated entity tokens to enable efficient, full-space prediction.<n>We first introduce specialized tokenization to construct feature representations at the level of dedicated entity tokens.<n>We then fuse pre-trained structural and textual features into these unified embeddings via a relation-guided gating mechanism.
  arXiv  Detail & Related papers  (2026-02-26T07:20:40Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• TreeDiff: AST-Guided Code Generation with Diffusion LLMs [27.111814602726227]
  We propose a syntax-aware diffusion framework that incorporates structural priors from Abstract Syntax Trees (ASTs) into the denoising process.<n>Results demonstrate that syntax-aware corruption significantly improves syntactic correctness, reconstruction accuracy, and generalization to unseen code patterns.
  arXiv  Detail & Related papers  (2025-08-02T19:46:09Z)
• Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment [53.2701026843921]
  Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
  arXiv  Detail & Related papers  (2023-08-24T17:56:46Z)
• Physics of Language Models: Part 1, Learning Hierarchical Language Structures [51.68385617116854]
  Transformer-based language models are effective but complex, and understanding their inner workings and reasoning mechanisms is a significant challenge.<n>We introduce a family of synthetic CFGs that produce hierarchical rules, capable of generating lengthy sentences.<n>We demonstrate that generative models like GPT can accurately learn and reason over CFG-defined hierarchies and generate sentences based on it.
  arXiv  Detail & Related papers  (2023-05-23T04:28:16Z)

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.