mlsanityData to 14 Oct 2026

From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop

arXiv 2608.11171 ↗First posted 11 Aug 2026cs.CL cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

The Workshop on Trustworthy Natural Language Processing (TrustNLP), co-located with major ACL conferences since 2021, has grown from 8 proceedings papers to 41 over six editions, documenting a field-wide transition from post-hoc interpretability of static models to mechanistic understanding and proactive control of generative systems. We synthesize insights from all 144 proceedings papers, classifying them along six trust dimensions grounded in established frameworks (TrustLLM, DecodingTrust). We observe co-occurrences with capability emergence. The release of the first high-impact chat models activated all trust dimensions simultaneously, while subsequent model generations shifted focus toward truthfulness and safety alignment. Analysis from the classification study reveals that truthfulness is the fastest-growing dimension (absent in 2021-2022, comprising 37% of papers by 2025-2026), fairness remains the most consistent theme, and explainability exhibits a U-shaped trajectory; declining as post-hoc methods lost relevance but resurging in 2026 through mechanistic interpretability. A cross-venue comparison with ACL, NAACL, EACL, and EMNLP (~2K papers) in the same period shows that TrustNLP's topical distribution closely follows the field average. We identify four structural insights and conclude with actionable directions for the research community.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 67 references that are in the map. First posted on arXiv 11 Aug 2026.

Builds on

41 of 67 references.

References · 41

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  3. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  4. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  5. 2020Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scanscited by 158
  6. 2022On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representationscited by 75
  7. 2024Estimating Knowledge in Large Language Models Without Generating a Single Tokencited by 40
  8. 2024Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinementcited by 29
  9. 2024Intrinsic Test of Unlearning Using Parametric Knowledge Tracescited by 29
  10. 2022Challenges in Applying Explainability Methods to Improve the Fairness of NLP Modelscited by 20
  11. 2023Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Modelscited by 20
  12. 2025On the Robustness of Agentic Function Callingcited by 19
29 more
  1. 2023Privacy- and Utility-Preserving NLP with Anonymized Data: A case study of Pseudonymizationcited by 18
  2. 2024PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximizationcited by 17
  3. 2025"Don't Forget the Teachers": Towards an Educator-Centered Understanding of Harms from Large Language Models in Educationcited by 14
  4. 2023Driving Context into Text-to-Text Privatizationcited by 13
  5. 2023Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wordingcited by 13
  6. 2025Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Riskcited by 13
  7. 2024FACTOID: FACtual enTailment fOr hallucInation Detectioncited by 10
  8. 2024Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretrainingcited by 10
  9. 2023Improving Factuality of Abstractive Summarization via Contrastive Reward Learningcited by 9
  10. 2023Examining the Causal Effect of First Names on Language Models: The Case of Social Commonsense Reasoningcited by 8
  11. 2024Cross-Task Defense: Instruction-Tuning LLMs for Content Safetycited by 8
  12. 2023On the Interplay between Fairness and Explainabilitycited by 7
  13. 2026Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignmentcited by 7
  14. 2026Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden Statescited by 7
  15. 2026Did You Forget What I Asked? Prospective Memory Failures in Large Language Modelscited by 6
  16. 2024Minimal Evidence Group Identification for Claim Verificationcited by 5
  17. 2024Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Scriptcited by 4
  18. 2026Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignmentcited by 4
  19. 2026Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selectioncited by 4
  20. 2024Automated Adversarial Discovery for Safety Classifierscited by 3
  21. 2025Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recallcited by 3
  22. 2023Sample Attackability in Natural Language Adversarial Attackscited by 2
  23. 2024The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classificationcited by 2
  24. 2026What are They Thinking? Delineation, Probing, and Tracking of Concepts in LLMscited by 2
  25. 2026Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategiescited by 2
  26. 2022A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twittercited by 1
  27. 2023Beyond Turing: A Comparative Analysis of Approaches for Detecting Machine-Generated Textcited by 1
  28. 2024Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threatscited by 1
  29. 2026The Geometry of Refusal: Linear Instability in Safety-Aligned LLMscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Establishing Trustworthiness: Rethinking Tasks and Model Evaluation
  2. 2025Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
  3. 2025SciTrust 2.0: A Comprehensive Framework for Evaluating Trustworthiness of Large Language Models in Scientific Applications
  4. 2026Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
  5. 2025A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
  6. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook
  7. 2023Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety
  8. 2024Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models