# Meaning Representations from Trajectories in Autoregressive Models

arXiv: https://arxiv.org/abs/2310.18348 · HTML: https://mlsanity.com/paper/2310.18348/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [SGPT: GPT Sentence Embeddings for Semantic Search](https://mlsanity.com/paper/2202.08904/) (2022)
- [An Unsupervised Sentence Embedding Method by Mutual Information Maximization](https://mlsanity.com/paper/2009.12061/) (2020)
- [Scaling Sentence Embeddings with Large Language Models](https://mlsanity.com/paper/2307.16645/) (2023)
- [Language Model Evaluation Beyond Perplexity](https://mlsanity.com/paper/2106.00085/) (2021)
- [PromptBERT: Improving BERT Sentence Embeddings with Prompts](https://mlsanity.com/paper/2201.04337/) (2022)
- [Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?](https://mlsanity.com/paper/2104.10809/) (2021)
- [Distributional Semantics and Linguistic Theory](https://mlsanity.com/paper/1905.01896/) (2019)
- [Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO](https://mlsanity.com/paper/2004.15020/) (2020)
- [SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features](https://mlsanity.com/paper/2206.07023/) (2022)
- [An enriched category theory of language: from syntax to semantics](https://mlsanity.com/paper/2106.07890/) (2021)
- [Taming AI Bots: Controllability of Neural States in Large Language Models](https://mlsanity.com/paper/2305.18449/) (2023)
- [Transparency Helps Reveal When Language Models Learn Meaning](https://mlsanity.com/paper/2210.07468/) (2022)

## Built on by (most cited first, 18 of 18)

- [Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs](https://mlsanity.com/paper/2412.11556/) (2024)
- [Meta-Task Prompting Elicits Embeddings from Large Language Models](https://mlsanity.com/paper/2402.18458/) (2024)
- [Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment](https://mlsanity.com/paper/2502.11401/) (2025)
- [Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering](https://mlsanity.com/paper/2505.12831/) (2025)
- [Interpretable Text Embeddings and Text Similarity Explanation: A Survey](https://mlsanity.com/paper/2502.14862/) (2025)
- [Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features](https://mlsanity.com/paper/2412.00142/) (2024)
- [Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare](https://mlsanity.com/paper/2509.07961/) (2025)
- [Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI](https://mlsanity.com/paper/2405.14061/) (2024)
- [The magnitude of categories of texts enriched by language models](https://mlsanity.com/paper/2501.06662/) (2025)
- [Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding](https://mlsanity.com/paper/2402.08919/) (2024)
- [Where's the Bug? Attention Probing for Scalable Fault Localization](https://mlsanity.com/paper/2502.13966/) (2025)
- [The Truth Lies Somewhere in the Middle (of the Generated Tokens)](https://mlsanity.com/paper/2605.09969/) (2026)
- [Directed Metric Structures arising in Large Language Models](https://mlsanity.com/paper/2405.12264/) (2024)
- [The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety](https://mlsanity.com/paper/2601.06116/) (2026)
- [How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy](https://mlsanity.com/paper/2508.09346/) (2025)
- [Prompting Complexity: Shortest Prompts for Texts and Behaviors in LLMs](https://mlsanity.com/paper/2607.06145/) (2026)
- [Conjuring Semantic Similarity](https://mlsanity.com/paper/2410.16431/) (2024)
- [Delta Activations: A Representation for Finetuned Large Language Models](https://mlsanity.com/paper/2509.04442/) (2025)

## Abstract (arXiv)

We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. Moreover, unlike vector-based representations, distribution-based representations can also model asymmetric relations (e.g., direction of logical entailment, hypernym/hyponym relations) by using algebraic operations between likelihood functions. These ideas are grounded in distributional perspectives on semantics and are connected to standard constructions in automata theory, but to our knowledge they have not been applied to modern language models. We empirically show that the representations obtained from large models align well with human annotations, outperform other zero-shot and prompt-free methods on semantic similarity tasks, and can be used to solve more complex entailment and containment tasks that standard embeddings cannot handle. Finally, we extend our method to represent data from different modalities (e.g., image and text) using multimodal autoregressive models. Our code is available at: https://github.com/tianyu139/meaning-as-trajectories