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

arXiv: https://arxiv.org/abs/2608.11171 · HTML: https://mlsanity.com/paper/2608.11171/

## 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 (most cited first, 30 of 41)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans](https://mlsanity.com/paper/2008.06388/) (2020)
- [On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations](https://mlsanity.com/paper/2203.13928/) (2022)
- [Estimating Knowledge in Large Language Models Without Generating a Single Token](https://mlsanity.com/paper/2406.12673/) (2024)
- [Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement](https://mlsanity.com/paper/2402.15180/) (2024)
- [Intrinsic Test of Unlearning Using Parametric Knowledge Traces](https://mlsanity.com/paper/2406.11614/) (2024)
- [Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models](https://mlsanity.com/paper/2206.03945/) (2022)
- [Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models](https://mlsanity.com/paper/2307.09209/) (2023)
- [On the Robustness of Agentic Function Calling](https://mlsanity.com/paper/2504.00914/) (2025)
- [Privacy- and Utility-Preserving NLP with Anonymized Data: A case study of Pseudonymization](https://mlsanity.com/paper/2306.05561/) (2023)
- [PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization](https://mlsanity.com/paper/2412.05892/) (2024)
- ["Don't Forget the Teachers": Towards an Educator-Centered Understanding of Harms from Large Language Models in Education](https://mlsanity.com/paper/2502.14592/) (2025)
- [Driving Context into Text-to-Text Privatization](https://mlsanity.com/paper/2306.01457/) (2023)
- [Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording](https://mlsanity.com/paper/2306.06199/) (2023)
- [Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk](https://mlsanity.com/paper/2502.15865/) (2025)
- [FACTOID: FACtual enTailment fOr hallucInation Detection](https://mlsanity.com/paper/2403.19113/) (2024)
- [Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining](https://mlsanity.com/paper/2410.18371/) (2024)
- [Improving Factuality of Abstractive Summarization via Contrastive Reward Learning](https://mlsanity.com/paper/2307.04507/) (2023)
- [Examining the Causal Effect of First Names on Language Models: The Case of Social Commonsense Reasoning](https://mlsanity.com/paper/2306.01117/) (2023)
- [Cross-Task Defense: Instruction-Tuning LLMs for Content Safety](https://mlsanity.com/paper/2405.15202/) (2024)
- [On the Interplay between Fairness and Explainability](https://mlsanity.com/paper/2310.16607/) (2023)
- [Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment](https://mlsanity.com/paper/2603.11388/) (2026)
- [Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States](https://mlsanity.com/paper/2606.02907/) (2026)
- [Did You Forget What I Asked? Prospective Memory Failures in Large Language Models](https://mlsanity.com/paper/2603.23530/) (2026)
- [Minimal Evidence Group Identification for Claim Verification](https://mlsanity.com/paper/2404.15588/) (2024)
- [Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script](https://mlsanity.com/paper/2412.02323/) (2024)
- [Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment](https://mlsanity.com/paper/2601.22313/) (2026)

## 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.