# Meaning without reference in large language models

arXiv: https://arxiv.org/abs/2208.02957 · HTML: https://mlsanity.com/paper/2208.02957/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 66 references that are in the map.
- First posted on arXiv 5 Aug 2022.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [Implicit Representations of Meaning in Neural Language Models](https://mlsanity.com/paper/2106.00737/) (2021)
- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)
- [Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color](https://mlsanity.com/paper/2109.06129/) (2021)
- [Learning Distributed Representations of Sentences from Unlabelled Data](https://mlsanity.com/paper/1602.03483/) (2016)
- [Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs](https://mlsanity.com/paper/2111.13654/) (2021)
- [MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models](https://mlsanity.com/paper/2010.00840/) (2020)
- [Shaking the foundations: delusions in sequence models for interaction and control](https://mlsanity.com/paper/2110.10819/) (2021)
- [Word meaning in minds and machines](https://mlsanity.com/paper/2008.01766/) (2020)
- [A Review of Winograd Schema Challenge Datasets and Approaches](https://mlsanity.com/paper/2004.13831/) (2020)
- [HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment](https://mlsanity.com/paper/1608.02117/) (2016)
- [Symbolic Behaviour in Artificial Intelligence](https://mlsanity.com/paper/2102.03406/) (2021)

## Built on by (most cited first, 30 of 76)

- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [The Debate Over Understanding in AI's Large Language Models](https://mlsanity.com/paper/2210.13966/) (2022)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Language Models as Agent Models](https://mlsanity.com/paper/2212.01681/) (2022)
- [Does CLIP Bind Concepts? Probing Compositionality in Large Image Models](https://mlsanity.com/paper/2212.10537/) (2022)
- [Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks](https://mlsanity.com/paper/2307.00175/) (2023)
- [Learning to Model the World with Language](https://mlsanity.com/paper/2308.01399/) (2023)
- [LLMs achieve adult human performance on higher-order theory of mind tasks](https://mlsanity.com/paper/2405.18870/) (2024)
- [Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting](https://mlsanity.com/paper/2401.15585/) (2024)
- [Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges](https://mlsanity.com/paper/2409.02387/) (2024)
- [From task structures to world models: What do LLMs know?](https://mlsanity.com/paper/2310.04276/) (2023)
- [Testing AI on language comprehension tasks reveals insensitivity to underlying meaning](https://mlsanity.com/paper/2302.12313/) (2023)
- [The Vector Grounding Problem](https://mlsanity.com/paper/2304.01481/) (2023)
- [Benchmarks as Microscopes: A Call for Model Metrology](https://mlsanity.com/paper/2407.16711/) (2024)
- [DALL-E 2 Fails to Reliably Capture Common Syntactic Processes](https://mlsanity.com/paper/2210.12889/) (2022)
- [Standards for Belief Representations in LLMs](https://mlsanity.com/paper/2405.21030/) (2024)
- [Dissociating language and thought in large language models](https://mlsanity.com/paper/2301.06627/) (2023)
- [Do Vision and Language Models Share Concepts? A Vector Space Alignment Study](https://mlsanity.com/paper/2302.06555/) (2023)
- [At the Dawn of Generative AI Era: A Tutorial-cum-Survey on New Frontiers in 6G Wireless Intelligence](https://mlsanity.com/paper/2402.18587/) (2024)
- [Language Models as Models of Language](https://mlsanity.com/paper/2408.07144/) (2024)
- [A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates](https://mlsanity.com/paper/2401.03910/) (2024)
- [Unpacking Large Language Models with Conceptual Consistency](https://mlsanity.com/paper/2209.15093/) (2022)
- [MEWL: Few-shot multimodal word learning with referential uncertainty](https://mlsanity.com/paper/2306.00503/) (2023)
- [Challenges of Large Language Models for Mental Health Counseling](https://mlsanity.com/paper/2311.13857/) (2023)
- [Large Language Model Benchmarks in Medical Tasks](https://mlsanity.com/paper/2410.21348/) (2024)
- [COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models](https://mlsanity.com/paper/2210.01963/) (2022)

## Abstract (arXiv)

The widespread success of large language models (LLMs) has been met with skepticism that they possess anything like human concepts or meanings. Contrary to claims that LLMs possess no meaning whatsoever, we argue that they likely capture important aspects of meaning, and moreover work in a way that approximates a compelling account of human cognition in which meaning arises from conceptual role. Because conceptual role is defined by the relationships between internal representational states, meaning cannot be determined from a model's architecture, training data, or objective function, but only by examination of how its internal states relate to each other. This approach may clarify why and how LLMs are so successful and suggest how they can be made more human-like.