---
title: "Workshop on Trustworthy NLP 2026 — all accepted papers"
description: "All 41 papers of Workshop on Trustworthy NLP 2026, the most cited first; those with our summary link to it."
canonical: "https://research.elamur.ai/free/en/venues/trustnlp/2026/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/trustnlp/2026/papers/)

[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](https://md.research.elamur.ai/free/en/venues/trustnlp/2026/) / papers

# Workshop on Trustworthy NLP 2026: all accepted papers

41 papers · the most cited first · [← Workshop on Trustworthy NLP 2026](https://md.research.elamur.ai/free/en/venues/trustnlp/2026/)

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://md.research.elamur.ai/free/en/papers/xue-2026-deactivating-refusal-triggers-understanding-mitigating/)**Zhiyu Xue, Zimo Qi, Guangliang Liu et al.*our summary*
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://md.research.elamur.ai/free/en/papers/yeh-2026-lexical-familiarity-predicts-processing-depth/)**Lang-Ching Yeh, Yu-Chieh Wang, Shu-Kai Hsieh*our summary*
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.
26. **[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/)**Krishna Kanth Nakka, Xue Jiang, Dmitrii Usynin et al.*our summary*
27. **[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/)**Zvi Topol*our summary*
28. **[ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking ↗](https://aclanthology.org/2026.trustnlp-main.21/)**Yanjun Lin, Zimo Xiao, Kartik Natarajan et al.
29. **[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/)**Noor Islam S. Mohammad, Ulug Bayazit*our summary*
30. **[Single-Layer Activation Edits Easily Corrupt Factual Recall but Rarely Repair It ↗](https://aclanthology.org/2026.trustnlp-main.38/)**Zacharie Bugaud
31. **[Teaching People LLM's Errors and Getting it Right](https://md.research.elamur.ai/free/en/papers/stringham-2026-teaching-people-llm-s-errors/)**Nathan Stringham, Fateme Hashemi Chaleshtori, Xinyuan Yan et al.*our summary*
32. **[The Conservative AI: Diagnosing Hold Bias and Reliability Limits in Persona-Based Monetary Policy Simulation ↗](https://aclanthology.org/2026.trustnlp-main.52/)**Giyong Kim, Sojung Kim
33. **[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/)**Shivam Ratnakar, Kartikeya Vats*our summary*
34. **[The Halo Effect and Language Takeover: Spatiotemporal Attention Decay Explains Vision-Language Model Failures in Simple Visual Counting](https://md.research.elamur.ai/free/en/papers/zhao-2026-halo-effect-language-takeover-spatiotemporal/)**Haochen Zhao, Sujian Li*our summary*
35. **[Toward Dialect-Aware Safety Evaluation for Arabic Large Language Models](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-dialect-aware-safety-evaluation-arabic/)**Wajdi Zaghouani*our summary*
36. **[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/)**Han-Yu Su, Kuan-Yu Chu, Yung-Hui Li et al.*our summary*
37. **[Uncertainty-Aware Proxy Attribute Reasoning for Reliable Media Bias Detection ↗](https://aclanthology.org/2026.trustnlp-main.4/)**Chin-Po Chen, Jeng-Lin Li, Ming-Ching Chang
38. **[Understanding the Effects of Safety Unalignment on Reasoning- and Instruction-Tuned Large Language Models ↗](https://aclanthology.org/2026.trustnlp-main.20/)**John Timothy Halloran
39. **[What are They Thinking? Delineation, Probing, and Tracking of Concepts in LLMs ↗](https://aclanthology.org/2026.trustnlp-main.9/)**Mohamed Abdelwahab, Michelle Yu Collins, Sihan Chen et al.
40. **[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/)**Jiaming Qu, Mengtian Guo, Yue Wang*our summary*
41. **[With a Grain of SALT: Are LLMs Fair Across Social Dimensions? ↗](https://aclanthology.org/2026.trustnlp-main.48/)**Samee Arif, Zohaib Khan, Maaidah Kaleem Butt et al.
- [← back to](https://md.research.elamur.ai/free/en/venues/trustnlp/2026/) — Workshop on Trustworthy NLP 2026