HumT DumT: Measuring and controlling human-like language in LLMs

• URL: http://arxiv.org/abs/2502.13259v1
• Date: Tue, 18 Feb 2025 20:04:09 GMT
• Title: HumT DumT: Measuring and controlling human-like language in LLMs
• Authors: Myra Cheng, Sunny Yu, Dan Jurafsky,
• Abstract summary: Human-like language might improve user experience, but might also lead to overreliance and stereotyping.<n>We introduce HumT and SocioT, metrics for human-like tone and other dimensions of social perceptions in text data.<n>By measuring HumT across preference and usage datasets, we find that users prefer less human-like outputs from LLMs.
• Score: 29.82328120944693
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Should LLMs generate language that makes them seem human? Human-like language might improve user experience, but might also lead to overreliance and stereotyping. Assessing these potential impacts requires a systematic way to measure human-like tone in LLM outputs. We introduce HumT and SocioT, metrics for human-like tone and other dimensions of social perceptions in text data based on relative probabilities from an LLM. By measuring HumT across preference and usage datasets, we find that users prefer less human-like outputs from LLMs. HumT also offers insights into the impacts of anthropomorphism: human-like LLM outputs are highly correlated with warmth, social closeness, femininity, and low status, which are closely linked to the aforementioned harms. We introduce DumT, a method using HumT to systematically control and reduce the degree of human-like tone while preserving model performance. DumT offers a practical approach for mitigating risks associated with anthropomorphic language generation.

Related papers

• If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs [55.8331366739144]
  We introduce LIFESTATE-BENCH, a benchmark designed to assess lifelong learning in large language models (LLMs) Our fact checking evaluation probes models' self-awareness, episodic memory retrieval, and relationship tracking, across both parametric and non-parametric approaches.
  arXiv  Detail & Related papers  (2025-03-30T16:50:57Z)
• Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication [0.09999629695552195]
  We investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) We show that referentially grounded vocabularies emerge that enable reliable communication in all conditions, even when humans and LLMs collaborate.
  arXiv  Detail & Related papers  (2025-03-06T12:47:54Z)
• Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina [7.155982875107922]
  Studies suggest large language models (LLMs) can exhibit human-like reasoning, aligning with human behavior in economic experiments, surveys, and political discourse.<n>This has led many to propose that LLMs can be used as surrogates or simulations for humans in social science research.<n>We assess the reasoning depth of LLMs using the 11-20 money request game.
  arXiv  Detail & Related papers  (2024-10-25T14:46:07Z)
• Judgment of Learning: A Human Ability Beyond Generative Artificial Intelligence [0.0]
  Large language models (LLMs) increasingly mimic human cognition in various language-based tasks. We introduce a cross-agent prediction model to assess whether ChatGPT-based LLMs align with human judgments of learning (JOL) Our results revealed that while human JOL reliably predicted actual memory performance, none of the tested LLMs demonstrated comparable predictive accuracy.
  arXiv  Detail & Related papers  (2024-10-17T09:42:30Z)
• Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance [73.19687314438133]
  We study how reliance is affected by contextual features of an interaction. We find that contextual characteristics significantly affect human reliance behavior. Our results show that calibration and language quality alone are insufficient in evaluating the risks of human-LM interactions.
  arXiv  Detail & Related papers  (2024-07-10T18:00:05Z)
• A Survey on Human Preference Learning for Large Language Models [81.41868485811625]
  The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning. This survey covers the sources and formats of preference feedback, the modeling and usage of preference signals, as well as the evaluation of the aligned LLMs.
  arXiv  Detail & Related papers  (2024-06-17T03:52:51Z)
• Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension [63.330262740414646]
  We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs) We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
  arXiv  Detail & Related papers  (2024-02-28T04:56:21Z)
• Divergences between Language Models and Human Brains [59.100552839650774]
  We systematically explore the divergences between human and machine language processing. We identify two domains that LMs do not capture well: social/emotional intelligence and physical commonsense. Our results show that fine-tuning LMs on these domains can improve their alignment with human brain responses.
  arXiv  Detail & Related papers  (2023-11-15T19:02:40Z)
• Psychometric Predictive Power of Large Language Models [32.31556074470733]
  We find that instruction tuning does not always make large language models human-like from a cognitive modeling perspective. Next-word probabilities estimated by instruction-tuned LLMs are often worse at simulating human reading behavior than those estimated by base LLMs.
  arXiv  Detail & Related papers  (2023-11-13T17:19:14Z)
• Do LLMs exhibit human-like response biases? A case study in survey design [66.1850490474361]
  We investigate the extent to which large language models (LLMs) reflect human response biases, if at all. We design a dataset and framework to evaluate whether LLMs exhibit human-like response biases in survey questionnaires. Our comprehensive evaluation of nine models shows that popular open and commercial LLMs generally fail to reflect human-like behavior.
  arXiv  Detail & Related papers  (2023-11-07T15:40:43Z)
• Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks [12.723777984461693]
  Large language models (LLMs) are remarkable data annotators. Crowdsourcing, an important, inexpensive way to obtain human annotations, may itself be impacted by LLMs. We estimate that 33-46% of crowd workers used LLMs when completing a task.
  arXiv  Detail & Related papers  (2023-06-13T16:46:24Z)

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.