Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026)

Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor 2026-07 Association for Computational Linguistics San Diego, California text conference publication 979-8-89176-418-7 trustnlp-2026-main https://aclanthology.org/2026.trustnlp-main.0/ Evaluating Cross-Lingual Behavior and Consistency of Multimodal Large Language Models Hao Wang author Pinzhi Huang author Daisuke Kawahara author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 wang-etal-2026-evaluating-cross https://aclanthology.org/2026.trustnlp-main.1/ 2026-07 1 20 Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall Qianli Wang author Mingyang Wang author Nils Feldhus author Simon Ostermann author Yuan Cao author Hinrich Schuetze author Sebastian Möller author Vera Schmitt author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 wang-etal-2026-compressed https://aclanthology.org/2026.trustnlp-main.2/ 2026-07 21 39 Uncertainty-Aware Proxy Attribute Reasoning for Reliable Media Bias Detection Chin-Po Chen author Jeng-Lin Li author Ming-Ching Chang author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 chen-etal-2026-uncertainty-aware-proxy https://aclanthology.org/2026.trustnlp-main.4/ 2026-07 40 63 Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis Zvi Topol author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 topol-2026-quantifying https://aclanthology.org/2026.trustnlp-main.5/ 2026-07 64 72 ClaimCLAIRE: A Trust-Aware Multi-Component Fact-Checking Agent for Open-World Claims Xinman Liu author Mayank Sharma author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 liu-sharma-2026-claimclaire https://aclanthology.org/2026.trustnlp-main.6/ 2026-07 73 91 ChatbotManip: a Dataset to Facilitate Evaluation and Oversight of Manipulative Chatbot Behaviour Jack Luigi Henry Contro author Simrat Deol author Martim Brandao author Yulan He author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 contro-etal-2026-chatbotmanip https://aclanthology.org/2026.trustnlp-main.7/ 2026-07 92 107 Controllable Pareto Trade-off between Fairness and Accuracy Yongkang Du author Jieyu Zhao author Yijun Yang author Tianyi Zhou author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 du-etal-2026-controllable https://aclanthology.org/2026.trustnlp-main.8/ 2026-07 108 120 What are They Thinking? Delineation, Probing, and Tracking of Concepts in LLMs Mohamed Abdelwahab author Michelle Yu Collins author Sihan Chen author Yi Cheng Zhao author Zafarullah Mahmood author Jiading Zhu author Soliman Ali author Jonathan Rose author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 abdelwahab-etal-2026-thinking https://aclanthology.org/2026.trustnlp-main.9/ 2026-07 121 179 Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment Yavuz Faruk Bakman author Duygu Nur Yaldiz author Salman Avestimehr author Sai Praneeth Karimireddy author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 bakman-etal-2026-hair https://aclanthology.org/2026.trustnlp-main.10/ 2026-07 180 203 Teaching People LLM’s Errors and Getting it Right Nathan Stringham author Fateme Hashemi Chaleshtori author Xinyuan Yan author Zhichao Xu author Bei Wang author Ana Marasovic author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 stringham-etal-2026-teaching https://aclanthology.org/2026.trustnlp-main.11/ 2026-07 204 226 Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States Subramanyam Sahoo author Vinija Jain author Aman Chadha author Divya Chaudhary author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 sahoo-etal-2026-linear https://aclanthology.org/2026.trustnlp-main.12/ 2026-07 227 239 KoLegalQA: A Korean Legal QA Dataset for Trustworthy and Explanation-Grounded Legal AI Yongtae Lee author Surin Lee author Sumin Kim author S M Wahidur Rahman author Heung-No Lee author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 lee-etal-2026-kolegalqa https://aclanthology.org/2026.trustnlp-main.13/ 2026-07 240 255 Authorization-First Retrieval: Enforcing Least Privilege in Multi-Agent RAG Systems Rohith Namboothiri author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 namboothiri-2026-authorization https://aclanthology.org/2026.trustnlp-main.15/ 2026-07 256 271 PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage Krishna Kanth Nakka author Xue Jiang author Dmitrii Usynin author Xuebing Zhou author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 nakka-etal-2026-pii https://aclanthology.org/2026.trustnlp-main.16/ 2026-07 272 286 Coercion Suppression Increases Preference Hallucinations via a Deceptive Bypass in K-Level Negotiation Agents Jihye Kim author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 kim-2026-coercion https://aclanthology.org/2026.trustnlp-main.17/ 2026-07 287 294 Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations Mamnuya Rinki author Chahat Raj author Anjishnu Mukherjee author Ziwei Zhu author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 rinki-etal-2026-purdah https://aclanthology.org/2026.trustnlp-main.18/ 2026-07 295 315 Ghost Context: Measuring Cross-Context Interference in Long-Context Language Models Rohith Namboothiri author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 namboothiri-2026-ghost https://aclanthology.org/2026.trustnlp-main.19/ 2026-07 316 329 Understanding the Effects of Safety Unalignment on Reasoning- and Instruction-Tuned Large Language Models John Timothy Halloran author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 halloran-2026-understanding https://aclanthology.org/2026.trustnlp-main.20/ 2026-07 330 341 ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking Yanjun Lin author Zimo Xiao author Kartik Natarajan author Mahesh Sankaranarayanan author Niraj Nawanit author Rakshit Parashar author Austin Zhang author Karthik Konaraddi author Rishita Mote author Wei Niu author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 lin-etal-2026-reactod https://aclanthology.org/2026.trustnlp-main.21/ 2026-07 342 352 Geometric Deviation as an Unsupervised Pre-Generation Reliability Signal: Probing LLM Representations for Answerability Yucheng Du author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 du-2026-geometric https://aclanthology.org/2026.trustnlp-main.22/ 2026-07 353 363 Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection Yusser Al Ghussin author Daniil Gurgurov author Tanja Baeumel author Josef Van Genabith author Patrick Schramowski author Simon Ostermann author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 al-ghussin-etal-2026-multilingual https://aclanthology.org/2026.trustnlp-main.24/ 2026-07 364 401 Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment Zhiyu Xue author Zimo Qi author Guangliang Liu author Bocheng Chen author Ramtin Pedarsani author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 xue-etal-2026-deactivating https://aclanthology.org/2026.trustnlp-main.26/ 2026-07 402 412 A Systematic Taxonomy of Failure Modes in Retrieval-Augmented Generation Systems Anupama Garani author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 garani-2026-systematic https://aclanthology.org/2026.trustnlp-main.27/ 2026-07 413 424 Improving the Faithfulness of LLM-based Abstractive Summarization with Span-level Unlikelihood Training Sicong Huang author Qianqi Yan author Shengze Wang author Ian Lane author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 huang-etal-2026-improving https://aclanthology.org/2026.trustnlp-main.28/ 2026-07 425 438 Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs Jinhwa Kim author Ian Harris author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 kim-harris-2026-context https://aclanthology.org/2026.trustnlp-main.29/ 2026-07 439 455 Lexical Familiarity Predicts Processing Depth for Nonliteral Language in Large Language Models Lang-Ching Yeh author Yu-Chieh Wang author Shu-Kai Hsieh author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 yeh-etal-2026-lexical https://aclanthology.org/2026.trustnlp-main.32/ 2026-07 456 470 Did You Forget What I Asked? Prospective Memory Failures in Large Language Models Avni Mittal author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 mittal-2026-forget https://aclanthology.org/2026.trustnlp-main.33/ 2026-07 471 488 Don’t Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese Rian Touchent author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 touchent-2026-dont https://aclanthology.org/2026.trustnlp-main.35/ 2026-07 489 502 Toward Dialect-Aware Safety Evaluation for Arabic Large Language Models Wajdi Zaghouani author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 zaghouani-2026-toward https://aclanthology.org/2026.trustnlp-main.37/ 2026-07 503 514 Single-Layer Activation Edits Easily Corrupt Factual Recall but Rarely Repair It Zacharie Bugaud author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 bugaud-2026-single https://aclanthology.org/2026.trustnlp-main.38/ 2026-07 515 527 Truth or Dare: Analyzing LLM Susceptibility to External Evidence of Varying Factuality Han-Yu Su author Kuan-Yu Chu author Yung-Hui Li author Lun-Wei Ku author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 su-etal-2026-truth https://aclanthology.org/2026.trustnlp-main.39/ 2026-07 528 538 The Halo Effect and Language Takeover: Spatiotemporal Attention Decay Explains Vision-Language Model Failures in Simple Visual Counting Haochen Zhao author Sujian Li author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 zhao-li-2026-halo https://aclanthology.org/2026.trustnlp-main.40/ 2026-07 539 545 Why is “Chicago” Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues Jiaming Qu author Mengtian Guo author Yue Wang author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 qu-etal-2026-chicago https://aclanthology.org/2026.trustnlp-main.41/ 2026-07 546 556 Domain-Dependent Safety Behavior in Open-Weight LLMs: An Empirical Study Across Seven Ethical Domains Zacharie Bugaud author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 bugaud-2026-domain https://aclanthology.org/2026.trustnlp-main.42/ 2026-07 557 562 A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification Stephanie Brandl author Oliver Eberle author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 brandl-eberle-2026-systematic https://aclanthology.org/2026.trustnlp-main.44/ 2026-07 563 583 Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs Amr Hegazy author Mostafa Elhoushi author Amr Alanwar author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 hegazy-etal-2026-guiding https://aclanthology.org/2026.trustnlp-main.46/ 2026-07 584 599 SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization Noor Islam S Mohammad author Ulug Bayazit author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 mohammad-bayazit-2026-surgellm https://aclanthology.org/2026.trustnlp-main.47/ 2026-07 600 617 With a Grain of SALT: Are LLMs Fair Across Social Dimensions? Samee Arif author Zohaib Khan author Maaidah Kaleem Butt author Muhammad Suhaib Rashid author Agha Ali Raza author Awais Athar author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 arif-etal-2026-grain https://aclanthology.org/2026.trustnlp-main.48/ 2026-07 618 636 GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning Kasidit Sermsri author Teerapong Panboonyuen author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 sermsri-panboonyuen-2026-gatekd https://aclanthology.org/2026.trustnlp-main.49/ 2026-07 637 652 The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs Shivam Ratnakar author Kartikeya Vats author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 ratnakar-vats-2026-geometry https://aclanthology.org/2026.trustnlp-main.51/ 2026-07 653 662 The Conservative AI: Diagnosing Hold Bias and Reliability Limits in Persona-Based Monetary Policy Simulation Giyong Kim author Sojung Kim author 2026-07 text Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026) Kai-Wei Chang editor Ninareh Mehrabi editor Satyapriya Krishna editor Anubrata Das editor Jwala Dhamala editor Yang Trista Cao editor Tharindu Kumarage editor Anil Ramakrishna editor Christos Christodoulopoulos editor Yixin Wan editor Aram Galystan editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics San Diego, California conference publication 979-8-89176-418-7 kim-kim-2026-conservative https://aclanthology.org/2026.trustnlp-main.52/ 2026-07 663 677