Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks

• URL: http://arxiv.org/abs/2405.10632v5
• Date: Fri, 12 Jul 2024 15:59:53 GMT
• Title: Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks
• Authors: Lujain Ibrahim, Saffron Huang, Lama Ahmad, Markus Anderljung,
• Abstract summary: "Human interaction evaluations" focus on the assessment of human-model interactions. We propose a safety-focused HIE design framework with three stages. We conclude with tangible recommendations for addressing concerns over costs, replicability, and unrepresentativeness of HIEs.
• Score: 1.3309842610191835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model evaluations are central to understanding the safety, risks, and societal impacts of AI systems. While most real-world AI applications involve human-AI interaction, most current evaluations (e.g., common benchmarks) of AI models do not. Instead, they incorporate human factors in limited ways, assessing the safety of models in isolation, thereby falling short of capturing the complexity of human-model interactions. In this paper, we discuss and operationalize a definition of an emerging category of evaluations -- "human interaction evaluations" (HIEs) -- which focus on the assessment of human-model interactions or the process and the outcomes of humans using models. First, we argue that HIEs can be used to increase the validity of safety evaluations, assess direct human impact and interaction-specific harms, and guide future assessments of models' societal impact. Second, we propose a safety-focused HIE design framework -- containing a human-LLM interaction taxonomy -- with three stages: (1) identifying the risk or harm area, (2) characterizing the use context, and (3) choosing the evaluation parameters. Third, we apply our framework to two potential evaluations for overreliance and persuasion risks. Finally, we conclude with tangible recommendations for addressing concerns over costs, replicability, and unrepresentativeness of HIEs.

Related papers

• ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Models [53.00812898384698]
  We argue that human evaluation of generative large language models (LLMs) should be a multidisciplinary undertaking. We highlight how cognitive biases can conflate fluent information and truthfulness, and how cognitive uncertainty affects the reliability of rating scores such as Likert. We propose the ConSiDERS-The-Human evaluation framework consisting of 6 pillars -- Consistency, Scoring Criteria, Differentiating, User Experience, Responsible, and Scalability.
  arXiv  Detail & Related papers  (2024-05-28T22:45:28Z)
• AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents [65.16893197330589]
  Large Language Models (LLMs) have demonstrated their ability to replicate human behaviors across a wide range of scenarios. However, their capability in handling complex, multi-character social interactions has yet to be fully explored. We introduce the Multi-Agent Interaction Evaluation Framework (AntEval), encompassing a novel interaction framework and evaluation methods.
  arXiv  Detail & Related papers  (2024-01-12T11:18:00Z)
• Sociotechnical Safety Evaluation of Generative AI Systems [13.546708226350963]
  Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. We propose a three-layered framework that takes a structured, sociotechnical approach to evaluating these risks.
  arXiv  Detail & Related papers  (2023-10-18T14:13:58Z)
• It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density Estimation [15.8765167340819]
  Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation such as data annotation and system assessment. Human perception and behaviour during human evaluation exhibit inherent variability due to diverse cognitive processes and subjective interpretations. This paper introduces a novel meta-learning framework that treats HAS as a zero-shot density estimation problem.
  arXiv  Detail & Related papers  (2023-09-30T20:54:59Z)
• Towards Objective Evaluation of Socially-Situated Conversational Robots: Assessing Human-Likeness through Multimodal User Behaviors [26.003947740875482]
  This paper focuses on assessing the human-likeness of the robot as the primary evaluation metric. Our approach aims to evaluate the robot's human-likeness based on observable user behaviors indirectly, thus enhancing objectivity and objectivity.
  arXiv  Detail & Related papers  (2023-08-21T20:21:07Z)
• Evaluating Human-Language Model Interaction [79.33022878034627]
  We develop a new framework, Human-AI Language-based Interaction Evaluation (HALIE), that defines the components of interactive systems. We design five tasks to cover different forms of interaction: social dialogue, question answering, crossword puzzles, summarization, and metaphor generation. We find that better non-interactive performance does not always translate to better human-LM interaction.
  arXiv  Detail & Related papers  (2022-12-19T18:59:45Z)
• Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation [136.16507050034755]
  Existing human evaluation studies for summarization either exhibit a low inter-annotator agreement or have insufficient scale. We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which is based on fine-grained semantic units. We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of 22,000 summary-level annotations over 28 top-performing systems.
  arXiv  Detail & Related papers  (2022-12-15T17:26:05Z)
• Are Neural Topic Models Broken? [81.15470302729638]
  We study the relationship between automated and human evaluation of topic models. We find that neural topic models fare worse in both respects compared to an established classical method.
  arXiv  Detail & Related papers  (2022-10-28T14:38:50Z)
• Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach [84.02388020258141]
  We propose a new framework named ENIGMA for estimating human evaluation scores based on off-policy evaluation in reinforcement learning. ENIGMA only requires a handful of pre-collected experience data, and therefore does not involve human interaction with the target policy during the evaluation. Our experiments show that ENIGMA significantly outperforms existing methods in terms of correlation with human evaluation scores.
  arXiv  Detail & Related papers  (2021-02-20T03:29:20Z)

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.