From Automation to Collaboration: Human-in-the-Loop Methods for Safe and Trustworthy NLP

• URL: http://arxiv.org/abs/2605.25226v1
• Date: Sun, 24 May 2026 19:27:20 GMT
• Title: From Automation to Collaboration: Human-in-the-Loop Methods for Safe and Trustworthy NLP
• Abstract summary: Large language models are widely deployed in high-stakes NLP tasks, yet risks as bias, hallucination, adversarial vulnerability and unreliable generalization remain.<n>This survey examines recent human-in-the-loop methods that shift NLP from automation toward collaboration for safety and robustness.
• Score: 0.28675177318965045
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language models are widely deployed in high-stakes NLP tasks, yet risks such as bias, hallucination, adversarial vulnerability and unreliable generalization remain. Probe-based auditing reveals inconsistencies in model behavior. Adversarial text generation uncovers robustness gaps, especially in lower-resourced languages with limited benchmarks. Enterprise text-to-SQL settings expose the difficulty of validating outputs over private and large-scale databases. Human supervision is essential for probe validation, adversarial verification and domain-specific annotation, but it is costly and hard to scale. This survey examines recent human-in-the-loop methods that shift NLP from automation toward collaboration for safety and trustworthiness. We review how human expertise supports auditing, robustness evaluation, data construction and model steering. Our findings highlight gaps in scalable probing, sustainable robustness benchmarks, low-resource settings and governance of private systems. We outline practical research directions for adaptive auditing, collaborative evaluation and accountable deployment.

Related papers

• Silent Failures in Federated Personalization of Foundation Models [6.116163085721452]
  "Silent Failures" include amplified bias, fairness collapse, and alignment erosion.<n>We introduce a taxonomy of six silent failure modes arising from the interaction of foundation model personalization, dataset shift, and core federated constraints.<n>We conclude with a research agenda for privacy-preserving behavioral evaluation and propose that silent failures become a standard diagnostic category for trustworthy federated artificial intelligence.
  arXiv  Detail & Related papers  (2026-05-31T01:33:11Z)
• CompliBench: Benchmarking LLM Judges for Compliance Violation Detection in Dialogue Systems [19.083967725767387]
  CompliBench is a novel benchmark designed to evaluate the ability of LLM judges to detect and localize guideline violations in multi-turn dialogues.<n>We develop a scalable, automated data generation pipeline that simulates user-agent interactions.<n>Our controllable flaw injection process automatically yields precise ground-truth labels for the violated guideline and the exact conversation turn.
  arXiv  Detail & Related papers  (2026-04-14T05:42:41Z)
• Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models [7.9049991577473735]
  Recent work has shown that large language models (LLMs) can serve as reliable privacy evaluators, achieving strong agreement with human judgments.<n>We address this gap by distilling the privacy assessment capabilities of Mistral Large 3 (675B) into lightweight encoder models with as few as 150M parameters.
  arXiv  Detail & Related papers  (2026-03-31T09:40:58Z)
• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• Qualitative Coding Analysis through Open-Source Large Language Models: A User Study and Design Recommendations [0.037282630026096594]
  ChatQDA is an on-device framework powered by open-source LLMs for privacy-preserving open coding.<n>Our mixed-methods user study reveals that participants rated the system highly for usability and perceived efficiency.<n>We conclude with design recommendations for local-first analysis tools that prioritize verifiable privacy and methodological rigor.
  arXiv  Detail & Related papers  (2026-02-20T17:04:02Z)
• Confidence Estimation for LLMs in Multi-turn Interactions [48.081802290688394]
  This work presents the first systematic study of confidence estimation in multi-turn interactions.<n>We establish a formal evaluation framework grounded in two key desideratas: per-turn calibration and monotonicity of confidence.<n>Our work provides a foundational methodology for developing more reliable and trustworthy conversational agents.
  arXiv  Detail & Related papers  (2026-01-05T14:58:04Z)
• Can Large Language Models Express Uncertainty Like Human? [71.27418419522884]
  We release the first diverse, large-scale dataset of hedging expressions with human-annotated confidence scores.<n>We conduct the first systematic study of linguistic confidence across modern large language models.
  arXiv  Detail & Related papers  (2025-09-29T02:34:30Z)
• Evaluating Language Model Reasoning about Confidential Information [95.64687778185703]
  We study whether language models exhibit contextual robustness, or the capability to adhere to context-dependent safety specifications.<n>We develop a benchmark (PasswordEval) that measures whether language models can correctly determine when a user request is authorized.<n>We find that current open- and closed-source models struggle with this seemingly simple task, and that, perhaps surprisingly, reasoning capabilities do not generally improve performance.
  arXiv  Detail & Related papers  (2025-08-27T15:39:46Z)
• Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge [1.1666234644810893]
  Small models outperform larger ones in safety, suggesting that training and architecture may matter more than scale.<n>No model is fully robust to adversarial elicitation, with jailbreak attacks using low-resource languages or refusal suppression proving effective.
  arXiv  Detail & Related papers  (2025-04-10T16:00:59Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)

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.