Eliciting Human Preferences with Language Models

• URL: http://arxiv.org/abs/2310.11589v1
• Date: Tue, 17 Oct 2023 21:11:21 GMT
• Title: Eliciting Human Preferences with Language Models
• Authors: Belinda Z. Li, Alex Tamkin, Noah Goodman, Jacob Andreas
• Abstract summary: Language models (LMs) can be directed to perform target tasks by using labeled examples or natural language prompts. We propose to use *LMs themselves* to guide the task specification process. We study GATE in three domains: email validation, content recommendation, and moral reasoning.
• Score: 56.68637202313052
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models (LMs) can be directed to perform target tasks by using labeled examples or natural language prompts. But selecting examples or writing prompts for can be challenging--especially in tasks that involve unusual edge cases, demand precise articulation of nebulous preferences, or require an accurate mental model of LM behavior. We propose to use *LMs themselves* to guide the task specification process. In this paper, we introduce **Generative Active Task Elicitation (GATE)**: a learning framework in which models elicit and infer intended behavior through free-form, language-based interaction with users. We study GATE in three domains: email validation, content recommendation, and moral reasoning. In preregistered experiments, we show that LMs prompted to perform GATE (e.g., by generating open-ended questions or synthesizing informative edge cases) elicit responses that are often more informative than user-written prompts or labels. Users report that interactive task elicitation requires less effort than prompting or example labeling and surfaces novel considerations not initially anticipated by users. Our findings suggest that LM-driven elicitation can be a powerful tool for aligning models to complex human preferences and values.

Related papers

• Exploring Prompt Engineering Practices in the Enterprise [3.7882262667445734]
  A prompt is a natural language instruction designed to elicit certain behaviour or output from a model. For complex tasks and tasks with specific requirements, prompt design is not trivial. We analyze sessions of prompt editing behavior, categorizing the parts of prompts users iterated on and the types of changes they made.
  arXiv  Detail & Related papers  (2024-03-13T20:32:32Z)
• Customizing Language Model Responses with Contrastive In-Context Learning [7.342346948935483]
  We propose an approach that uses contrastive examples to better describe our intent. This involves providing positive examples that illustrate the true intent, along with negative examples that show what characteristics we want LLMs to avoid. Before generating an answer, we ask the model to analyze the examples to teach itself what to avoid. This reasoning step provides the model with the appropriate articulation of the user's need and guides it towards generting a better answer.
  arXiv  Detail & Related papers  (2024-01-30T19:13:12Z)
• Helping Language Models Learn More: Multi-dimensional Task Prompt for Few-shot Tuning [36.14688633670085]
  We propose MTPrompt, a multi-dimensional task prompt learning method based on task-related object, summary, and task description information. By automatically building and searching for appropriate prompts, our proposed MTPrompt achieves the best results on few-shot samples setting and five different datasets.
  arXiv  Detail & Related papers  (2023-12-13T10:00:44Z)
• RecExplainer: Aligning Large Language Models for Explaining Recommendation Models [50.74181089742969]
  Large language models (LLMs) have demonstrated remarkable intelligence in understanding, reasoning, and instruction following. This paper presents the initial exploration of using LLMs as surrogate models to explain black-box recommender models. To facilitate an effective alignment, we introduce three methods: behavior alignment, intention alignment, and hybrid alignment.
  arXiv  Detail & Related papers  (2023-11-18T03:05:43Z)
• Syntax and Semantics Meet in the "Middle": Probing the Syntax-Semantics Interface of LMs Through Agentivity [68.8204255655161]
  We present the semantic notion of agentivity as a case study for probing such interactions. This suggests LMs may potentially serve as more useful tools for linguistic annotation, theory testing, and discovery.
  arXiv  Detail & Related papers  (2023-05-29T16:24:01Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)
• Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models [116.25562358482962]
  State-of-the-art neural language models can be used to solve ad-hoc language tasks without the need for supervised training. PromptIDE allows users to experiment with prompt variations, visualize prompt performance, and iteratively optimize prompts.
  arXiv  Detail & Related papers  (2022-08-16T17:17:53Z)
• Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents [111.33545170562337]
  We investigate the possibility of grounding high-level tasks, expressed in natural language, to a chosen set of actionable steps. We find that if pre-trained LMs are large enough and prompted appropriately, they can effectively decompose high-level tasks into low-level plans. We propose a procedure that conditions on existing demonstrations and semantically translates the plans to admissible actions.
  arXiv  Detail & Related papers  (2022-01-18T18:59:45Z)
• Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm [0.0]
  We discuss methods of prompt programming, emphasizing the usefulness of considering prompts through the lens of natural language. We introduce the idea of a metaprompt that seeds the model to generate its own natural language prompts for a range of tasks.
  arXiv  Detail & Related papers  (2021-02-15T05:27:55Z)
• AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts [46.03503882865222]
  AutoPrompt is an automated method to create prompts for a diverse set of tasks based on a gradient-guided search. We show that masked language models (MLMs) have an inherent capability to perform sentiment analysis and natural language inference without additional parameters or finetuning.
  arXiv  Detail & Related papers  (2020-10-29T22:54:00Z)

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.