Can large language models explore in-context?
- URL: http://arxiv.org/abs/2403.15371v3
- Date: Mon, 28 Oct 2024 19:55:46 GMT
- Title: Can large language models explore in-context?
- Authors: Akshay Krishnamurthy, Keegan Harris, Dylan J. Foster, Cyril Zhang, Aleksandrs Slivkins,
- Abstract summary: We deploy Large Language Models as agents in simple multi-armed bandit environments.
We find that the models do not robustly engage in exploration without substantial interventions.
- Score: 87.49311128190143
- License:
- Abstract: We investigate the extent to which contemporary Large Language Models (LLMs) can engage in exploration, a core capability in reinforcement learning and decision making. We focus on native performance of existing LLMs, without training interventions. We deploy LLMs as agents in simple multi-armed bandit environments, specifying the environment description and interaction history entirely in-context, i.e., within the LLM prompt. We experiment with GPT-3.5, GPT-4, and Llama2, using a variety of prompt designs, and find that the models do not robustly engage in exploration without substantial interventions: i) Across all of our experiments, only one configuration resulted in satisfactory exploratory behavior: GPT-4 with chain-of-thought reasoning and an externally summarized interaction history, presented as sufficient statistics; ii) All other configurations did not result in robust exploratory behavior, including those with chain-of-thought reasoning but unsummarized history. Although these findings can be interpreted positively, they suggest that external summarization -- which may not be possible in more complex settings -- is important for obtaining desirable behavior from LLM agents. We conclude that non-trivial algorithmic interventions, such as fine-tuning or dataset curation, may be required to empower LLM-based decision making agents in complex settings.
Related papers
- Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.
Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.
We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
arXiv Detail & Related papers (2025-02-04T17:26:58Z) - Enhancing LLM's Ability to Generate More Repository-Aware Unit Tests Through Precise Contextual Information Injection [4.367526927436771]
Large Language Models (LLMs) guided by prompt engineering have gained attention for their ability to handle a broad range of tasks.
LLMs may exhibit hallucinations when generating unit tests for focal methods or functions due to their lack of awareness regarding the project's global context.
We propose RATester, which enhances the LLM's ability to generate more repository-aware unit tests.
arXiv Detail & Related papers (2025-01-13T15:43:36Z) - 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) - GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.
GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
arXiv Detail & Related papers (2024-10-11T03:05:06Z) - Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases.
We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning.
Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
arXiv Detail & Related papers (2024-06-19T00:28:58Z) - Intuitive or Dependent? Investigating LLMs' Behavior Style to
Conflicting Prompts [9.399159332152013]
This study investigates the behaviors of Large Language Models (LLMs) when faced with conflicting prompts versus their internal memory.
This will help to understand LLMs' decision mechanism and also benefit real-world applications, such as retrieval-augmented generation (RAG)
arXiv Detail & Related papers (2023-09-29T17:26:03Z) - Can Large Language Models Understand Real-World Complex Instructions? [54.86632921036983]
Large language models (LLMs) can understand human instructions, but struggle with complex instructions.
Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions.
We propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically.
arXiv Detail & Related papers (2023-09-17T04:18:39Z) - Prompting Large Language Models for Counterfactual Generation: An
Empirical Study [13.506528217009507]
Large language models (LLMs) have made remarkable progress in a wide range of natural language understanding and generation tasks.
We present a comprehensive evaluation framework on various types of NLU tasks, which covers all key factors in determining LLMs' capability of generating counterfactuals.
arXiv Detail & Related papers (2023-05-24T06:44:32Z)
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.