Representation in large language models

• URL: http://arxiv.org/abs/2501.00885v1
• Date: Wed, 01 Jan 2025 16:19:48 GMT
• Title: Representation in large language models
• Authors: Cameron C. Yetman,
• Abstract summary: I argue that Large Language Models behavior is partially driven by representation-based information processing. I describe techniques for investigating these representations and developing explanations.
• Score: 0.0
• License:
• Abstract: The extraordinary success of recent Large Language Models (LLMs) on a diverse array of tasks has led to an explosion of scientific and philosophical theorizing aimed at explaining how they do what they do. Unfortunately, disagreement over fundamental theoretical issues has led to stalemate, with entrenched camps of LLM optimists and pessimists often committed to very different views of how these systems work. Overcoming stalemate requires agreement on fundamental questions, and the goal of this paper is to address one such question, namely: is LLM behavior driven partly by representation-based information processing of the sort implicated in biological cognition, or is it driven entirely by processes of memorization and stochastic table look-up? This is a question about what kind of algorithm LLMs implement, and the answer carries serious implications for higher level questions about whether these systems have beliefs, intentions, concepts, knowledge, and understanding. I argue that LLM behavior is partially driven by representation-based information processing, and then I describe and defend a series of practical techniques for investigating these representations and developing explanations on their basis. The resulting account provides a groundwork for future theorizing about language models and their successors.

Related papers

• The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding [65.28200190598082]
  We propose a summative assessment over a carefully designed physical concept understanding task, PhysiCo. Our task alleviates the issue via the usage of grid-format inputs that abstractly describe physical phenomena. A comprehensive study on our task demonstrates: (1) state-of-the-art LLMs, including GP-4o, lag behind humans by 40%; (2) the parrot, o1 phenomenon is present in LLMs as they fail on our grid task but can describe and recognize the same concepts well in natural language.
  arXiv  Detail & Related papers  (2025-02-13T04:00:03Z)
• A Survey on Large Language Models with some Insights on their Capabilities and Limitations [0.3222802562733786]
  Large Language Models (LLMs) exhibit remarkable performance across various language-related tasks. LLMs have demonstrated emergent abilities extending beyond their core functions. This paper explores the foundational components, scaling mechanisms, and architectural strategies that drive these capabilities.
  arXiv  Detail & Related papers  (2025-01-03T21:04:49Z)
• Language Agents Meet Causality -- Bridging LLMs and Causal World Models [50.79984529172807]
  We propose a framework that integrates causal representation learning with large language models. This framework learns a causal world model, with causal variables linked to natural language expressions. We evaluate the framework on causal inference and planning tasks across temporal scales and environmental complexities.
  arXiv  Detail & Related papers  (2024-10-25T18:36:37Z)
• Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models [6.922021128239465]
  Recent advances in AI have been driven by the capabilities of large language models (LLMs) This paper introduces a framework that is both theoretical and practical, aimed at assessing how effectively LLMs are able to replicate real-world reasoning mechanisms.
  arXiv  Detail & Related papers  (2024-08-15T15:19:11Z)
• What Do Language Models Learn in Context? The Structured Task Hypothesis [89.65045443150889]
  Large language models (LLMs) learn a novel task from in-context examples presented in a demonstration, termed in-context learning (ICL) One popular hypothesis explains ICL by task selection. Another popular hypothesis is that ICL is a form of meta-learning, i.e., the models learn a learning algorithm at pre-training time and apply it to the demonstration.
  arXiv  Detail & Related papers  (2024-06-06T16:15:34Z)
• FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
  Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
  arXiv  Detail & Related papers  (2024-02-29T21:05:37Z)
• Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models [54.21695754082441]
  We propose a framework to teach Large Language Models (LLMs) to generate explainable stock predictions. A reflective agent learns how to explain past stock movements through self-reasoning, while the PPO trainer trains the model to generate the most likely explanations. Our framework can outperform both traditional deep-learning and LLM methods in prediction accuracy and Matthews correlation coefficient.
  arXiv  Detail & Related papers  (2024-02-06T03:18:58Z)
• From Understanding to Utilization: A Survey on Explainability for Large Language Models [27.295767173801426]
  This survey underscores the imperative for increased explainability in Large Language Models (LLMs) Our focus is primarily on pre-trained Transformer-based LLMs, which pose distinctive interpretability challenges due to their scale and complexity. When considering the utilization of explainability, we explore several compelling methods that concentrate on model editing, control generation, and model enhancement.
  arXiv  Detail & Related papers  (2024-01-23T16:09:53Z)
• The Quo Vadis of the Relationship between Language and Large Language Models [3.10770247120758]
  Large Language Models (LLMs) have come to encourage the adoption of LLMs as scientific models of language. We identify the most important theoretical and empirical risks brought about by the adoption of scientific models that lack transparency. We conclude that, at their current stage of development, LLMs hardly offer any explanations for language.
  arXiv  Detail & Related papers  (2023-10-17T10:54:24Z)
• MAML and ANIL Provably Learn Representations [60.17417686153103]
  We prove that two well-known meta-learning methods, MAML and ANIL, are capable of learning common representation among a set of given tasks. Specifically, in the well-known multi-task linear representation learning setting, they are able to recover the ground-truth representation at an exponentially fast rate. Our analysis illuminates that the driving force causing MAML and ANIL to recover the underlying representation is that they adapt the final layer of their model.
  arXiv  Detail & Related papers  (2022-02-07T19:43:02Z)

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.