LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users

• URL: http://arxiv.org/abs/2406.17737v1
• Date: Tue, 25 Jun 2024 17:24:07 GMT
• Title: LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users
• Authors: Elinor Poole-Dayan, Deb Roy, Jad Kabbara,
• Abstract summary: We investigate how the quality of Large Language Models responses changes in terms of information accuracy, truthfulness, and refusals depending on user traits. Our findings suggest that undesirable behaviors in state-of-the-art LLMs occur disproportionately more for users with lower English proficiency, of lower education status, and originating from outside the US.
• Score: 17.739596091065856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While state-of-the-art Large Language Models (LLMs) have shown impressive performance on many tasks, there has been extensive research on undesirable model behavior such as hallucinations and bias. In this work, we investigate how the quality of LLM responses changes in terms of information accuracy, truthfulness, and refusals depending on three user traits: English proficiency, education level, and country of origin. We present extensive experimentation on three state-of-the-art LLMs and two different datasets targeting truthfulness and factuality. Our findings suggest that undesirable behaviors in state-of-the-art LLMs occur disproportionately more for users with lower English proficiency, of lower education status, and originating from outside the US, rendering these models unreliable sources of information towards their most vulnerable users.

Related papers

• Testing and Evaluation of Large Language Models: Correctness, Non-Toxicity, and Fairness [30.632260870411177]
  Large language models (LLMs) have rapidly penetrated into people's work and daily lives over the past few years. This thesis focuses on the correctness, non-toxicity, and fairness of LLMs from both software testing and natural language processing perspectives.
  arXiv  Detail & Related papers  (2024-08-31T22:21:04Z)
• Examining the Influence of Political Bias on Large Language Model Performance in Stance Classification [5.8229466650067065]
  We investigate whether large language models (LLMs) exhibit a tendency to more accurately classify politically-charged stances. Our findings reveal a statistically significant difference in the performance of LLMs across various politically oriented stance classification tasks. LLMs have poorer stance classification accuracy when there is greater ambiguity in the target the statement is directed towards.
  arXiv  Detail & Related papers  (2024-07-25T01:11:38Z)
• Modulating Language Model Experiences through Frictions [56.17593192325438]
  Over-consumption of language model outputs risks propagating unchecked errors in the short-term and damaging human capabilities in the long-term. We propose selective frictions for language model experiences, inspired by behavioral science interventions, to dampen misuse.
  arXiv  Detail & Related papers  (2024-06-24T16:31:11Z)
• The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition [74.04775677110179]
  In-context Learning (ICL) has emerged as a powerful paradigm for performing natural language tasks with Large Language Models (LLM) We show that LLMs have strong yet inconsistent priors in emotion recognition that ossify their predictions. Our results suggest that caution is needed when using ICL with larger LLMs for affect-centered tasks outside their pre-training domain.
  arXiv  Detail & Related papers  (2024-03-25T19:07:32Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• NoMIRACL: Knowing When You Don't Know for Robust Multilingual Retrieval-Augmented Generation [92.5132418788568]
  Retrieval-augmented generation (RAG) grounds large language model (LLM) output by leveraging external knowledge sources to reduce factual hallucinations. NoMIRACL is a human-annotated dataset for evaluating LLM robustness in RAG across 18 typologically diverse languages. We measure robustness using two metrics: (i) hallucination rate, measuring model tendency to hallucinate an answer, when the answer is not present in passages in the non-relevant subset, and (ii) error rate, measuring model inaccuracy to recognize relevant passages in the relevant subset.
  arXiv  Detail & Related papers  (2023-12-18T17:18:04Z)
• Are Large Language Models Good Fact Checkers: A Preliminary Study [26.023148371263012]
  Large Language Models (LLMs) have drawn significant attention due to their outstanding reasoning capabilities and extensive knowledge repository. This study aims to comprehensively evaluate various LLMs in tackling specific fact-checking subtasks.
  arXiv  Detail & Related papers  (2023-11-29T05:04:52Z)
• Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs [8.526956860672698]
  Large Language Models (LLMs) have gained immense attention due to their notable emergent capabilities. This study investigates the potential of LLMs as reliable assessors of factual consistency in summaries generated by text-generation models.
  arXiv  Detail & Related papers  (2023-11-01T17:42:45Z)
• Language Models Hallucinate, but May Excel at Fact Verification [89.0833981569957]
  Large language models (LLMs) frequently "hallucinate," resulting in non-factual outputs. Even GPT-3.5 produces factual outputs less than 25% of the time. This underscores the importance of fact verifiers in order to measure and incentivize progress.
  arXiv  Detail & Related papers  (2023-10-23T04:39:01Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• Evaluating the Capability of Large-scale Language Models on Chinese Grammatical Error Correction Task [10.597024796304016]
  Large-scale language models (LLMs) has shown remarkable capability in various of Natural Language Processing (NLP) tasks. This report explores the how large language models perform on Chinese grammatical error correction tasks.
  arXiv  Detail & Related papers  (2023-07-08T13:10:59Z)

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.