Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect

• URL: http://arxiv.org/abs/2509.12065v1
• Date: Mon, 15 Sep 2025 15:48:09 GMT
• Title: Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect
• Authors: Alina Klerings, Jannik Brinkmann, Daniel Ruffinelli, Simone Ponzetto,
• Abstract summary: We study the representation and control of two multidimensional hierarchical grammar phenomena - verb tense and aspect.<n>We show causal control over both grammatical features through concept steering across three generation tasks.<n>We find that steering strength, location, and duration are crucial parameters for reducing undesirable side effects such as topic shift.
• Score: 3.360832612971853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the representation and control of two multidimensional hierarchical grammar phenomena - verb tense and aspect - and for each, identify distinct, orthogonal directions in residual space using linear discriminant analysis. Next, we demonstrate causal control over both grammatical features through concept steering across three generation tasks. Then, we use these identified features in a case study to investigate factors influencing effective steering in multi-token generation. We find that steering strength, location, and duration are crucial parameters for reducing undesirable side effects such as topic shift and degeneration. Our findings suggest that models encode tense and aspect in structurally organized, human-like ways, but effective control of such features during generation is sensitive to multiple factors and requires manual tuning or automated optimization.

Related papers

• Detecting Machine-Generated Long-Form Content with Latent-Space Variables [54.07946647012579]
  Existing zero-shot detectors primarily focus on token-level distributions, which are vulnerable to real-world domain shifts. We propose a more robust method that incorporates abstract elements, such as event transitions, as key deciding factors to detect machine versus human texts.
  arXiv  Detail & Related papers  (2024-10-04T18:42:09Z)
• Exploring syntactic information in sentence embeddings through multilingual subject-verb agreement [1.4335183427838039]
  We take the approach of developing curated synthetic data on a large scale, with specific properties.<n>We use a new multiple-choice task and datasets, Blackbird Language Matrices, to focus on a specific grammatical structural phenomenon.<n>We show that despite having been trained on multilingual texts in a consistent manner, multilingual pretrained language models have language-specific differences.
  arXiv  Detail & Related papers  (2024-09-10T14:58:55Z)
• Successor Features for Efficient Multisubject Controlled Text Generation [48.37713738712319]
  We introduce SF-GEN, which is grounded in two primary concepts: successor features (SFs) and language model rectification. SF-GEN seamlessly integrates the two to enable dynamic steering of text generation with no need to alter the LLM's parameters. To the best of our knowledge, our research represents the first application of successor features in text generation.
  arXiv  Detail & Related papers  (2023-11-03T00:17:08Z)
• Linguistically Motivated Sign Language Segmentation [51.06873383204105]
  We consider two kinds of segmentation: segmentation into individual signs and segmentation into phrases. Our method is motivated by linguistic cues observed in sign language corpora. We replace the predominant IO tagging scheme with BIO tagging to account for continuous signing.
  arXiv  Detail & Related papers  (2023-10-21T10:09:34Z)
• Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS) [3.57486761615991]
  unified representations consistently achieves better cross-lingual synthesis with respect to both naturalness and accent. Separate representations tend to have an order of magnitude more tokens than unified ones, which may affect model capacity.
  arXiv  Detail & Related papers  (2022-07-04T16:14:57Z)
• Detecting Text Formality: A Study of Text Classification Approaches [78.11745751651708]
  This work proposes the first to our knowledge systematic study of formality detection methods based on statistical, neural-based, and Transformer-based machine learning methods. We conducted three types of experiments -- monolingual, multilingual, and cross-lingual. The study shows the overcome of Char BiLSTM model over Transformer-based ones for the monolingual and multilingual formality classification task.
  arXiv  Detail & Related papers  (2022-04-19T16:23:07Z)
• Modeling Target-Side Morphology in Neural Machine Translation: A Comparison of Strategies [72.56158036639707]
  Morphologically rich languages pose difficulties to machine translation. A large amount of differently inflected word surface forms entails a larger vocabulary. Some inflected forms of infrequent terms typically do not appear in the training corpus. Linguistic agreement requires the system to correctly match the grammatical categories between inflected word forms in the output sentence.
  arXiv  Detail & Related papers  (2022-03-25T10:13:20Z)
• Exemplar-Controllable Paraphrasing and Translation using Bitext [57.92051459102902]
  We adapt models from prior work to be able to learn solely from bilingual text (bitext) Our single proposed model can perform four tasks: controlled paraphrase generation in both languages and controlled machine translation in both language directions.
  arXiv  Detail & Related papers  (2020-10-12T17:02:50Z)
• Generative latent neural models for automatic word alignment [0.0]
  Variational autoencoders have been recently used in various of natural language processing to learn in an unsupervised way latent representations that are useful for language generation tasks. In this paper, we study these models for the task of word alignment and propose and assess several evolutions of a vanilla variational autoencoders. We demonstrate that these techniques can yield competitive results as compared to Giza++ and to a strong neural network alignment system for two language pairs.
  arXiv  Detail & Related papers  (2020-09-28T07:54:09Z)

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.