Benchmarking Distributional Alignment of Large Language Models

• URL: http://arxiv.org/abs/2411.05403v1
• Date: Fri, 08 Nov 2024 08:41:17 GMT
• Title: Benchmarking Distributional Alignment of Large Language Models
• Authors: Nicole Meister, Carlos Guestrin, Tatsunori Hashimoto,
• Abstract summary: Language models (LMs) are increasingly used as simulacra for people, yet their ability to match the distribution of views of a specific demographic group remains uncertain. We construct a dataset expanding beyond political values, create human baselines for this task, and evaluate the extent to which an LM can align with a particular group's opinion distribution. Our analysis reveals open problems regarding if, and how, LMs can be used to simulate humans, and that LLMs can more accurately describe the opinion distribution than simulate such distributions.
• Score: 43.0198231524816
• License:
• Abstract: Language models (LMs) are increasingly used as simulacra for people, yet their ability to match the distribution of views of a specific demographic group and be \textit{distributionally aligned} remains uncertain. This notion of distributional alignment is complex, as there is significant variation in the types of attributes that are simulated. Prior works have underexplored the role of three critical variables -- the question domain, steering method, and distribution expression method -- which motivates our contribution of a benchmark explicitly addressing these dimensions. We construct a dataset expanding beyond political values, create human baselines for this task, and evaluate the extent to which an LM can align with a particular group's opinion distribution to inform design choices of such simulation systems. Our analysis reveals open problems regarding if, and how, LMs can be used to simulate humans, and that LLMs can more accurately describe the opinion distribution than simulate such distributions.

Related papers

• View From Above: A Framework for Evaluating Distribution Shifts in Model Behavior [0.9043709769827437]
  Large language models (LLMs) are asked to perform certain tasks. How can we be sure that their learned representations align with reality? We propose a domain-agnostic framework for systematically evaluating distribution shifts.
  arXiv  Detail & Related papers  (2024-07-01T04:07:49Z)
• What Are the Odds? Language Models Are Capable of Probabilistic Reasoning [23.487484744911995]
  We focus on evaluating the probabilistic reasoning capabilities of language models (LMs) using idealized and real-world statistical distributions. We perform a systematic evaluation of state-of-the-art LMs on three tasks: estimating percentiles, drawing samples, and calculating probabilities.
  arXiv  Detail & Related papers  (2024-06-18T17:51:24Z)
• Generative Assignment Flows for Representing and Learning Joint Distributions of Discrete Data [2.6499018693213316]
  We introduce a novel generative model for the representation of joint probability distributions of a possibly large number of discrete random variables. The embedding of the flow via the Segre map in the meta-simplex of all discrete joint distributions ensures that any target distribution can be represented in principle. Our approach has strong motivation from first principles of modeling coupled discrete variables.
  arXiv  Detail & Related papers  (2024-06-06T21:58:33Z)
• Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation [73.58618024960968]
  An increasing number of studies are employing large language models (LLMs) as agents to emulate the sequential decision-making processes of humans. This arouses curiosity regarding the capacity of LLM agents to comprehend probability distributions. Our analysis indicates that LLM agents can understand probabilities, but they struggle with probability sampling.
  arXiv  Detail & Related papers  (2024-04-13T16:59:28Z)
• A Distributional Analogue to the Successor Representation [54.99439648059807]
  This paper contributes a new approach for distributional reinforcement learning. It elucidates a clean separation of transition structure and reward in the learning process. As an illustration, we show that it enables zero-shot risk-sensitive policy evaluation.
  arXiv  Detail & Related papers  (2024-02-13T15:35:24Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• Wrapped Distributions on homogeneous Riemannian manifolds [58.720142291102135]
  Control over distributions' properties, such as parameters, symmetry and modality yield a family of flexible distributions. We empirically validate our approach by utilizing our proposed distributions within a variational autoencoder and a latent space network model.
  arXiv  Detail & Related papers  (2022-04-20T21:25:21Z)
• Goal-oriented adaptive sampling under random field modelling of response probability distributions [0.6445605125467573]
  We consider cases where the spatial variation of response distributions does not only concern their mean and/or variance but also other features including for instance shape or uni-modality versus multi-modality. Our contributions build upon a non-parametric Bayesian approach to modelling the thereby induced fields of probability distributions.
  arXiv  Detail & Related papers  (2021-02-15T15:55:23Z)
• Implicit Distributional Reinforcement Learning [61.166030238490634]
  implicit distributional actor-critic (IDAC) built on two deep generator networks (DGNs) Semi-implicit actor (SIA) powered by a flexible policy distribution. We observe IDAC outperforms state-of-the-art algorithms on representative OpenAI Gym environments.
  arXiv  Detail & Related papers  (2020-07-13T02:52:18Z)

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.