# Semantic Fusion with Fuzzy-Membership Features for Controllable Language Modelling

arXiv: https://arxiv.org/abs/2509.13357 · HTML: https://mlsanity.com/paper/2509.13357/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 14 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [Learning Deep Transformer Models for Machine Translation](https://mlsanity.com/paper/1906.01787/) (2019)
- [Using the Output Embedding to Improve Language Models](https://mlsanity.com/paper/1608.05859/) (2016)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling](https://mlsanity.com/paper/1611.01462/) (2016)
- [On Extractive and Abstractive Neural Document Summarization with Transformer Language Models](https://mlsanity.com/paper/1909.03186/) (2019)

## Built on by (most cited first, 1 of 1)

- [Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors](https://mlsanity.com/paper/2606.31845/) (2026)

## Abstract (arXiv)

We propose semantic fusion, a lightweight scheme that augments a Transformer language model (LM) with a parallel, fuzzy-membership feature channel that encodes token-level semantics. Each token is represented by a vector of interpretable features (e.g. part-of-speech cues, shallow roles, boundary flags, sentiment polarity and strength) whose values are graded degrees from differentiable membership functions (e.g. power kernels). These per-token vectors form a sentence-level semantic matrix fused via a gated adapter into the LM. Training uses standard next-token prediction, an auxiliary loss that reconstructs the semantic features from hidden states, and a lightweight uniformizer that regularizes adjective-class distributions. On a synthetic two-clause corpus with held-out adjectives for out-of-distribution (OOD) control, semantic fusion improves perplexity and enables precise, user-controllable generation of polarity and punctuation while maintaining model simplicity. This approach adds only small overhead, remains fully compatible with tied input-output embeddings, and provides an interpretable pathway for conditioned natural language generation.