PERSONA: A Reproducible Testbed for Pluralistic Alignment

• URL: http://arxiv.org/abs/2407.17387v1
• Date: Wed, 24 Jul 2024 16:11:39 GMT
• Title: PERSONA: A Reproducible Testbed for Pluralistic Alignment
• Authors: Louis Castricato, Nathan Lile, Rafael Rafailov, Jan-Philipp Fränken, Chelsea Finn,
• Abstract summary: We introduce PERSONA, a test bed designed to evaluate and improve pluralistic alignment of language models. We procedurally generate diverse user profiles from US census data, resulting in 1,586 synthetic personas. We then generate a large-scale evaluation dataset containing 3,868 prompts and 317,200 feedback pairs.
• Score: 46.750587209286344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the plurality of user opinions, instead reinforcing majority viewpoints and marginalizing minority perspectives. We introduce PERSONA, a reproducible test bed designed to evaluate and improve pluralistic alignment of LMs. We procedurally generate diverse user profiles from US census data, resulting in 1,586 synthetic personas with varied demographic and idiosyncratic attributes. We then generate a large-scale evaluation dataset containing 3,868 prompts and 317,200 feedback pairs obtained from our synthetic personas. Leveraging this dataset, we systematically evaluate LM capabilities in role-playing diverse users, verified through human judges, and the establishment of both a benchmark, PERSONA Bench, for pluralistic alignment approaches as well as an extensive dataset to create new and future benchmarks. The full dataset and benchmarks are available here: https://www.synthlabs.ai/research/persona.

Related papers

• Aligning LLMs with Individual Preferences via Interaction [51.72200436159636]
  We train large language models (LLMs) that can ''interact to align'' We develop a multi-turn preference dataset containing 3K+ multi-turn conversations in tree structures. For evaluation, we establish the ALOE benchmark, consisting of 100 carefully selected examples and well-designed metrics to measure the customized alignment performance during conversations.
  arXiv  Detail & Related papers  (2024-10-04T17:48:29Z)
• PersoBench: Benchmarking Personalized Response Generation in Large Language Models [6.8046587254152735]
  We present a new benchmark, PersoBench, to evaluate the personalization ability of large language models (LLMs) in persona-aware dialogue generation. Our analysis, conducted on three well-known persona-aware datasets, evaluates multiple dimensions of response quality, including fluency, diversity, coherence, and personalization.
  arXiv  Detail & Related papers  (2024-10-04T07:29:41Z)
• PersonalLLM: Tailoring LLMs to Individual Preferences [11.717169516971856]
  We present a public benchmark, PersonalLLM, focusing on adapting LLMs to provide maximal benefits for a particular user. We curate open-ended prompts paired with many high-quality answers over which users would be expected to display heterogeneous latent preferences. Our dataset and generated personalities offer an innovative testbed for developing personalization algorithms.
  arXiv  Detail & Related papers  (2024-09-30T13:55:42Z)
• WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback [28.317315761271804]
  We introduce WildFeedback, a novel framework that leverages real-time, in-situ user interactions to create preference datasets that more accurately reflect authentic human values. We apply this framework to a large corpus of user-LLM conversations, resulting in a rich preference dataset that reflects genuine user preferences. Our experiments demonstrate that LLMs fine-tuned on WildFeedback exhibit significantly improved alignment with user preferences.
  arXiv  Detail & Related papers  (2024-08-28T05:53:46Z)
• A User-Centric Benchmark for Evaluating Large Language Models [39.538411572029005]
  Large Language Models (LLMs) are essential tools to collaborate with users on different tasks. Few benchmarks have covered the intended utilization of LLMs by real users. We benchmark 10 LLM services on their efficacy in satisfying user needs.
  arXiv  Detail & Related papers  (2024-04-22T07:32:03Z)
• On the steerability of large language models toward data-driven personas [98.9138902560793]
  Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs.
  arXiv  Detail & Related papers  (2023-11-08T19:01:13Z)
• Evaluation of Faithfulness Using the Longest Supported Subsequence [52.27522262537075]
  We introduce a novel approach to evaluate faithfulness of machine-generated text by computing the longest noncontinuous of the claim that is supported by the context. Using a new human-annotated dataset, we finetune a model to generate Longest Supported Subsequence (LSS) Our proposed metric demonstrates an 18% enhancement over the prevailing state-of-the-art metric for faithfulness on our dataset.
  arXiv  Detail & Related papers  (2023-08-23T14:18:44Z)
• Large Language Models are Diverse Role-Players for Summarization Evaluation [82.31575622685902]
  A document summary's quality can be assessed by human annotators on various criteria, both objective ones like grammar and correctness, and subjective ones like informativeness, succinctness, and appeal. Most of the automatic evaluation methods like BLUE/ROUGE may be not able to adequately capture the above dimensions. We propose a new evaluation framework based on LLMs, which provides a comprehensive evaluation framework by comparing generated text and reference text from both objective and subjective aspects.
  arXiv  Detail & Related papers  (2023-03-27T10:40:59Z)
• The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm [154.47590401735323]
  Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems. This paper focuses on a challenging scenario where a user has multiple categories of interests. We propose a novel method called textitDiversity-Promoting Collaborative Metric Learning (DPCML)
  arXiv  Detail & Related papers  (2022-09-30T08:02:18Z)

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.