---
title: "Workshop on Trustworthy NLP 2026 — accepted papers"
description: "Workshop on Trustworthy NLP 2026 — accepted papers: 16 papers in the Elamur Research library (San Diego, California), with our…"
canonical: "https://research.elamur.ai/free/en/venues/trustnlp/2026/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/trustnlp/2026/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/) / 2026

# Workshop on Trustworthy NLP 2026 — accepted papers

Workshop on Trustworthy NLP 2026 is the 2026 edition of the Workshop on Trustworthy NLP, held in San Diego, California, July 2026 (publisher: Association for Computational Linguistics). The ACL Anthology lists 41 papers of it; our library holds 16 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

📍 San Diego, California · 🗓 July 2026

[**41** papers in the proceedings](#all) · [**16** works in our library](https://md.research.elamur.ai/free/en/venues/trustnlp/2026/#works) · [**3** citations of these works](https://md.research.elamur.ai/free/en/venues/trustnlp/2026/#works)

## Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. **[Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall](https://md.research.elamur.ai/free/en/papers/wang-2026-through-compressed-lens-investigating-impact/)**Qianli Wang, Mingyang Wang, Nils Feldhus et al.*2 citations · our summary*
2. **[A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification ↗](https://aclanthology.org/2026.trustnlp-main.44/)**Stephanie Brandl, Oliver Eberle*1 citation*
3. **[KoLegalQA: A Korean Legal QA Dataset for Trustworthy and Explanation-Grounded Legal AI ↗](https://aclanthology.org/2026.trustnlp-main.13/)**Yongtae Lee, Surin Lee, Sumin Kim et al.*1 citation*
4. **[Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations](https://md.research.elamur.ai/free/en/papers/rinki-2026-purdah-patriarchy-evaluating-mitigating-south/)**Mamnuya Rinki, Chahat Raj, Anjishnu Mukherjee et al.*1 citation · our summary*

## All accepted papers (41)

The most cited first; 16 with our summary link to their page here, the others to the original.

1. **[Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall](https://md.research.elamur.ai/free/en/papers/wang-2026-through-compressed-lens-investigating-impact/)**Qianli Wang, Mingyang Wang, Nils Feldhus et al.*2 citations · our summary*
2. **[A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification ↗](https://aclanthology.org/2026.trustnlp-main.44/)**Stephanie Brandl, Oliver Eberle*1 citation*
3. **[KoLegalQA: A Korean Legal QA Dataset for Trustworthy and Explanation-Grounded Legal AI ↗](https://aclanthology.org/2026.trustnlp-main.13/)**Yongtae Lee, Surin Lee, Sumin Kim et al.*1 citation*
4. **[Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations](https://md.research.elamur.ai/free/en/papers/rinki-2026-purdah-patriarchy-evaluating-mitigating-south/)**Mamnuya Rinki, Chahat Raj, Anjishnu Mukherjee et al.*1 citation · our summary*
5. **[A Systematic Taxonomy of Failure Modes in Retrieval-Augmented Generation Systems ↗](https://aclanthology.org/2026.trustnlp-main.27/)**Anupama Garani
6. **[Authorization-First Retrieval: Enforcing Least Privilege in Multi-Agent RAG Systems](https://md.research.elamur.ai/free/en/papers/namboothiri-2026-authorization-first-retrieval-enforcing-least/)**Rohith Namboothiri*our summary*
7. **[ChatbotManip: a Dataset to Facilitate Evaluation and Oversight of Manipulative Chatbot Behaviour ↗](https://aclanthology.org/2026.trustnlp-main.7/)**Jack Luigi Henry Contro, Simrat Deol, Martim Brandao et al.
8. **[ClaimCLAIRE: A Trust-Aware Multi-Component Fact-Checking Agent for Open-World Claims ↗](https://aclanthology.org/2026.trustnlp-main.6/)**Xinman Liu, Mayank Sharma
9. **[Coercion Suppression Increases Preference Hallucinations via a Deceptive Bypass in $K$-Level Negotiation Agents ↗](https://aclanthology.org/2026.trustnlp-main.17/)**Jihye Kim
10. **[Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs ↗](https://aclanthology.org/2026.trustnlp-main.29/)**Jinhwa Kim, Ian Harris
11. **[Controllable Pareto Trade-off between Fairness and Accuracy ↗](https://aclanthology.org/2026.trustnlp-main.8/)**Yongkang Du, Jieyu Zhao, Yijun Yang et al.
12. **[Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment ↗](https://aclanthology.org/2026.trustnlp-main.26/)**Zhiyu Xue, Zimo Qi, Guangliang Liu et al.
13. **[Did You Forget What I Asked? Prospective Memory Failures in Large Language Models](https://md.research.elamur.ai/free/en/papers/mittal-2026-did-you-forget-what-i/)**Avni Mittal*our summary*
14. **[Domain-Dependent Safety Behavior in Open-Weight LLMs: An Empirical Study Across Seven Ethical Domains ↗](https://aclanthology.org/2026.trustnlp-main.42/)**Zacharie Bugaud
15. **[Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese](https://md.research.elamur.ai/free/en/papers/touchent-2026-don-t-want-your-llm/)**Rian Touchent*our summary*
16. **[Evaluating Cross-Lingual Behavior and Consistency of Multimodal Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2026-evaluating-cross-lingual-behavior-consistency/)**Hao Wang, Pinzhi Huang, Daisuke Kawahara*our summary*
17. **[GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning](https://md.research.elamur.ai/free/en/papers/sermsri-2026-gatekd-confidence-gated-closed-loop/)**Kasidit Sermsri, Teerapong Panboonyuen*our summary*
18. **[Geometric Deviation as an Unsupervised Pre-Generation Reliability Signal: Probing LLM Representations for Answerability ↗](https://aclanthology.org/2026.trustnlp-main.22/)**Yucheng Du
19. **[Ghost Context: Measuring Cross-Context Interference in Long-Context Language Models](https://md.research.elamur.ai/free/en/papers/namboothiri-2026-ghost-context-measuring-cross-context/)**Rohith Namboothiri*our summary*
20. **[Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs ↗](https://aclanthology.org/2026.trustnlp-main.46/)**Amr Hegazy, Mostafa Elhoushi, Amr Alanwar
21. **[Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment ↗](https://aclanthology.org/2026.trustnlp-main.10/)**Yavuz Faruk Bakman, Duygu Nur Yaldiz, Salman Avestimehr et al.
22. **[Improving the Faithfulness of LLM-based Abstractive Summarization with Span-level Unlikelihood Training ↗](https://aclanthology.org/2026.trustnlp-main.28/)**Sicong Huang, Qianqi Yan, Shengze Wang et al.
23. **[Lexical Familiarity Predicts Processing Depth for Nonliteral Language in Large Language Models ↗](https://aclanthology.org/2026.trustnlp-main.32/)**Lang-Ching Yeh, Yu-Chieh Wang, Shu-Kai Hsieh
24. **[Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States](https://md.research.elamur.ai/free/en/papers/sahoo-2026-linear-probes-detect-task-format/)**Subramanyam Sahoo, Vinija Jain, Aman Chadha et al.*our summary*
25. **[Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection ↗](https://aclanthology.org/2026.trustnlp-main.24/)**Yusser Al Ghussin, Daniil Gurgurov, Tanja Baeumel et al.

[See all 41 papers in Workshop on Trustworthy NLP 2026 — accepted papers →](https://md.research.elamur.ai/free/en/venues/trustnlp/2026/papers/)

## Papers with our summary in our library (16)

The most cited first (OpenAlex citations plus our library's).

1. **[Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall](https://md.research.elamur.ai/free/en/papers/wang-2026-through-compressed-lens-investigating-impact/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Qianli Wang, Mingyang Wang, Nils Feldhus, et al.*2026 · 2 citations*
2. **[Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations](https://md.research.elamur.ai/free/en/papers/rinki-2026-purdah-patriarchy-evaluating-mitigating-south/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Mamnuya Rinki, Chahat Raj, Anjishnu Mukherjee, et al.*2026 · 1 citation*
3. **[Did You Forget What I Asked? Prospective Memory Failures in Large Language Models](https://md.research.elamur.ai/free/en/papers/mittal-2026-did-you-forget-what-i/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Avni Mittal*2026*
4. **[SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization](https://md.research.elamur.ai/free/en/papers/mohammad-2026-surgellm-rethinking-multi-task-evaluation/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Noor Islam S. Mohammad, Ulug Bayazit*2026*
5. **[PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage](https://md.research.elamur.ai/free/en/papers/nakka-2026-pii-jailbreaking-llms-activation-steering/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Krishna Kanth Nakka, Xue Jiang, Dmitrii Usynin, et al.*2026*
6. **[Authorization-First Retrieval: Enforcing Least Privilege in Multi-Agent RAG Systems](https://md.research.elamur.ai/free/en/papers/namboothiri-2026-authorization-first-retrieval-enforcing-least/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Rohith Namboothiri*2026*
7. **[Ghost Context: Measuring Cross-Context Interference in Long-Context Language Models](https://md.research.elamur.ai/free/en/papers/namboothiri-2026-ghost-context-measuring-cross-context/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Rohith Namboothiri*2026*
8. **[Why is “Chicago” Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues](https://md.research.elamur.ai/free/en/papers/qu-2026-why-is-chicago-predictive-deceptive/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Jiaming Qu, Mengtian Guo, Yue Wang*2026*
9. **[The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs](https://md.research.elamur.ai/free/en/papers/ratnakar-2026-geometry-refusal-linear-instability-safety/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Shivam Ratnakar, Kartikeya Vats*2026*
10. **[Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States](https://md.research.elamur.ai/free/en/papers/sahoo-2026-linear-probes-detect-task-format/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Subramanyam Sahoo, Vinija Jain, Aman Chadha, et al.*2026*
11. **[GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning](https://md.research.elamur.ai/free/en/papers/sermsri-2026-gatekd-confidence-gated-closed-loop/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Kasidit Sermsri, Teerapong Panboonyuen*2026*
12. **[Teaching People LLM's Errors and Getting it Right](https://md.research.elamur.ai/free/en/papers/stringham-2026-teaching-people-llm-s-errors/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Nathan Stringham, Fateme Hashemi Chaleshtori, Xinyuan Yan, et al.*2026*
13. **[Truth or Dare: Analyzing LLM Susceptibility to External Evidence of Varying Factuality](https://md.research.elamur.ai/free/en/papers/su-2026-truth-or-dare-analyzing-llm/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Han-Yu Su, Kuan-Yu Chu, Yung-Hui Li, et al.*2026*
14. **[Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis](https://md.research.elamur.ai/free/en/papers/topol-2026-quantifying-llm-safety-degradation-under/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Zvi Topol*2026*
15. **[Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese](https://md.research.elamur.ai/free/en/papers/touchent-2026-don-t-want-your-llm/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Rian Touchent*2026*
16. **[Evaluating Cross-Lingual Behavior and Consistency of Multimodal Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2026-evaluating-cross-lingual-behavior-consistency/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Hao Wang, Pinzhi Huang, Daisuke Kawahara*2026*

## Top topics

Topics of its works in our library, with the number of works on each.

[Language models & pretraining (11)](https://md.research.elamur.ai/free/en/topics/language-models/) · [Multilingual & cross-lingual NLP (2)](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Reasoning (2)](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Bias, fairness & safety (2)](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Efficient models & compression (2)](https://md.research.elamur.ai/free/en/topics/efficient-models/) · [Evaluation & benchmarks (1)](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Information retrieval & search (1)](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · [Interpretability (1)](https://md.research.elamur.ai/free/en/topics/interpretability/) · [Vision & language (1)](https://md.research.elamur.ai/free/en/topics/multimodal/)

## Fields

[Computer Science (16)](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities (12)](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Social Sciences (8)](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Psychology (1)](https://md.research.elamur.ai/free/en/shelves/psychology/)

## Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

[🧑‍🔬**Rohith Namboothiri**2 works here](https://md.research.elamur.ai/free/en/authors/rohith-namboothiri/) · [🧑‍🔬**Hinrich Schuetze**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/hinrich-schuetze/) · [🧑‍🔬**Mingyang Wang**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/mingyang-wang/) · [🧑‍🔬**Nils Feldhus**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/nils-feldhus/) · [🧑‍🔬**Qianli Wang**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/qianli-wang/) · [🧑‍🔬**Sebastian Möller**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/sebastian-moller/) · [🧑‍🔬**Simon Ostermann**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/simon-ostermann/) · [🧑‍🔬**Vera Schmitt**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/vera-schmitt/) · [🧑‍🔬**Yuan Cao**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/yuan-cao/) · [🧑‍🔬**Chahat Raj**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/chahat-raj/) · [🧑‍🔬**Ziwei Zhu**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/ziwei-zhu/) · [🧑‍🔬**Aman Chadha**1 work here](https://md.research.elamur.ai/free/en/authors/aman-chadha/)

## Top institutions

Institutions on the bylines of its works here, by the number of works.

[🎓**University of North Carolina at Chapel Hill** Chapel Hill · United States 1 work here](https://md.research.elamur.ai/free/en/universities/university-of-north-carolina-at-chapel-hill/) · [🎓**University of Southern California** Los Angeles · United States 1 work here](https://md.research.elamur.ai/free/en/universities/university-of-southern-california/) · [🏢**Microsoft** Redmond · United States 1 work here](https://md.research.elamur.ai/free/en/companies/microsoft/) · [🎓**Northeastern University** Boston · United States 1 work here](https://md.research.elamur.ai/free/en/universities/northeastern-university/) · [🏢**Google** Mountain View · United States 1 work here](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**Waseda University** Tokyo · Japan 1 work here](https://md.research.elamur.ai/free/en/universities/waseda-university/) · [🎓**Chulalongkorn University** Bangkok · Thailand 1 work here](https://md.research.elamur.ai/free/en/universities/chulalongkorn-university/) · [🎓**National Taiwan University** Taipei · Taiwan 1 work here](https://md.research.elamur.ai/free/en/universities/national-taiwan-university/) · [🎓**University of Utah** Salt Lake City · United States 1 work here](https://md.research.elamur.ai/free/en/universities/university-of-utah/) · [🔬**German Research Centre for Artificial Intelligence** Kaiserslautern · Germany 1 work here](https://md.research.elamur.ai/free/en/labs/german-research-centre-for-artificial-intelligence/) · [🏢**Google DeepMind** London · United Kingdom 1 work here](https://md.research.elamur.ai/free/en/companies/google-deepmind/) · [🎓**Technische Universität Berlin** Berlin · Germany 1 work here](https://md.research.elamur.ai/free/en/universities/technische-universitat-berlin/)

Place and dates from the event's site or the ACL Anthology; works and citations from OpenAlex and our library.

- [← previous Workshop on Trustworthy NLP 2023](https://md.research.elamur.ai/free/en/venues/trustnlp/2023/)
- [↑ back to Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)