OUT-OF-DISTRIBUTION

PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains (2022.tacl-1)

Challenge:	Pre-trained language models (PLMs) are gaining popularity on many benchmarks, but it is uncertain whether they can handle inputs that have been distributionally shifted.
Approach:	They evaluated various PETL techniques to detect out-of-distribution changes as the size of the PLM grows or the transfer methods are altered.
Outcome:	The proposed methods can detect out-of-distribution changes as the size of the PLM grows or the transfer methods are altered.

Copied to clipboard

Eyal Ben-David, Nadav Oved, Roi Reichart

BARLE: Background-Aware Representation Learning for Background Shift Out-of-Distribution Detection (2022.findings-emnlp)

Challenge:	Domain Adaptation (DA) algorithms suffer degradation when applied to out-of-distribution examples.
Approach:	They propose an example-based autoregressive Prompt learning algorithm for on-the-fly Any-Domain Adaptation . the algorithm is trained to generate a unique prompt that maps the test example to a semantic space .
Outcome:	The proposed model outperforms baselines in 14 multi-source adaptation scenarios.

Copied to clipboard

Hanyu Duan, Yi Yang, Ahmed Abbasi, Kar Yan Tam

MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering (2020.emnlp-main)

Challenge:	Existing methods for OOD detection focus on identifying semantic-shift OOD samples . background-shift detection is more practical but challenging .
Approach:	They propose a background-aware representation learning approach for background-shift OOD detection in NLP.
Outcome:	The proposed method improves background-shift OOD detection while maintaining ID classification accuracy.

Copied to clipboard

Tejas Gokhale, Pratyay Banerjee, Chitta Baral, Yezhou Yang

Multimodality

Challenge:	Availability of large-scale datasets has enabled statistical machine learning in vision and language understanding.
Approach:	They propose a training paradigm that exposes models to perceptually similar mutations of input . they show a 10.57% improvement in the VQA-CP challenge .
Outcome:	The proposed training paradigm improves on the visual question answering challenge with 10.57% accuracy.

Who Needs Decoders? Efficient Estimation of Sequence-Level Attributes with Proxies (2024.eacl-long)

Copied to clipboard

Yassir Fathullah, Puria Radmard, Adian Liusie, Mark Gales

Text Generation

Challenge:	Autoregressive decoding is expensive for many sequence-to-sequence tasks, but for some downstream tasks, the actual decoding output is not needed, just attributes of the sequence.
Approach:	They propose non-autoregressive proxy models that can efficiently predict scalar-valued sequence-level attributes from the encodings, avoiding the expensive decoding stage.
Outcome:	The proposed models outperform ensembles in machine translation (MT) and automatic speech recognition (ASR) while being significantly faster.

Leveraging Generative Large Language Models with Visual Instruction and Demonstration Retrieval for Multimodal Sarcasm Detection (2024.naacl-long)

Copied to clipboard

Binghao Tang, Boda Lin, Haolong Yan, Si Li

Multimodality

Challenge:	Existing methods for multimodal sarcasm detection do not fully utilize cross-modal features, limiting their performance on in-domain datasets.
Approach:	They propose a multimodal sarcasm detection model with a designed instruction template and a demonstration retrieval module.
Outcome:	The proposed model outperforms existing methods on in-domain datasets and achieves state-of-the-art performance.

Purging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness (2026.findings-acl)

Copied to clipboard

Hao An, Yibin Lou, Jiayi Guo, Yang Xu

Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding (2023.eacl-main)

Challenge:	Existing abstention fine-tuning methods cause models to suffer from label noise near the decision boundaries.
Approach:	They propose a latent space representation perspective for abstention fine-tuning . they propose 'geometric denoising' framework that constructs a truth hyperplane .
Outcome:	The proposed framework significantly enhances model truthfulness and demonstrates strong generalization in out-of-distribution scenarios.

Copied to clipboard

Mengnan Du, Subhabrata Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Hassan Awadallah

AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accents (2024.findings-eacl)

Challenge:	Recent studies have focused on compressing pre-trained language models (PLMs) however, few studies have examined the impact of compression on generalizability and robustness of compressed models for out-of-distribution data.
Approach:	They propose to use knowledge distillation and pruning to reduce model generalization and generalization on out-of-distribution data.
Outcome:	The proposed compression techniques overfit on shortcut samples and generalize poorly on hard ones.

Copied to clipboard

Abraham Owodunni, Aditya Yadavalli, Chris Emezue, Tobi Olatunji, Clinton Mbataku

Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities (2023.eacl-main)

Challenge:	AccentFold uses spatial relationships to improve speech recognition for accented speech . existing methods for accent recognition have been limited due to data scarcity and budget constraints .
Approach:	They propose a method that exploits spatial relationships between learned accent embeddings to improve downstream automatic speech recognition.
Outcome:	The proposed method outperforms baseline methods in accented speech training.

Copied to clipboard

Ali Modarressi, Hossein Amirkhani, Mohammad Taher Pilehvar

Tracr-Injection: Distilling Algorithms into Pre-trained Language Models (2025.findings-acl)

Challenge:	Several proposals have been put forward for improving out-of-distribution performance by mitigating dataset biases.
Approach:	They propose a fine-tuning strategy that incorporates the similarity between the main and biased model attribution scores in a Product of Experts (PoE) loss function to further improve OOD performance.
Outcome:	The proposed method improves OOD performance while maintaining in-distribution performance.

Copied to clipboard

Tomás Vergara Browne, Alvaro Soto

Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value Identification (2025.emnlp-industry)

Challenge:	Recent efforts to characterize symbolic abilities of the transformer architecture have shown that the tasks that can be implemented in RASP are uncommon to learn from natural unsupervised data.
Approach:	They propose a programming language, called RASP, which can be directly compiled into transformer weights to implement these algorithms.
Outcome:	The proposed method improves out-of-distribution performance compared to baselines, indicating that indeed a more symbolic mechanism is taking place in the inner workings of the model.

Copied to clipboard

Huike Zou, Haiyang Yang, Yindu Su, Chen Li Yu, Qinye Xie, Chengbao Lian, Qingheng Zhang, Shuguang Han, Fei Huang, Jufeng Chen

Information Retrieval

Challenge:	Existing methods for product attribute value identification suffer from cascading errors and lack of generalization capability.
Approach:	They propose a multi-level retrieval scheme that uses products and attribute values as distinct hierarchical levels in PAVI domain.
Outcome:	The proposed method performs better than the state-of-the-art methods on a real-world industrial dataset.

Towards Stable Natural Language Understanding via Information Entropy Guided Debiasing (2023.acl-long)

Copied to clipboard

Li Du, Xiao Ding, Zhouhao Sun, Ting Liu, Bing Qin, Jingshuo Liu

On Continual Model Refinement in Out-of-Distribution Data Streams (2022.acl-long)

Challenge:	Existing approaches to debiase Natural Language Understanding models use dataset biases instead of learning the intended task.
Approach:	They propose a debiasing framework that detects and purifies dataset biases using information entropy.
Outcome:	The proposed framework improves the stability of performance on out-of-distribution datasets for a set of widely adopted NLU models.

Copied to clipboard

Bill Yuchen Lin, Sida Wang, Xi Lin, Robin Jia, Lin Xiao, Xiang Ren, Scott Yih

Challenge:	Existing continual learning (CL) problems cannot cover real-world scenarios such as out-of-distribution errors.
Approach:	They propose a continual model refinement problem formulation to solve this problem . they extend several existing continual learning approaches to the CMR problem based on a general sampling algorithm .
Outcome:	The proposed model refinement solution improves on existing models and their performance metrics.

ER-Test: Evaluating Explanation Regularization Methods for Language Models (2022.findings-emnlp)

Copied to clipboard

Brihi Joshi, Aaron Chan, Ziyi Liu, Shaoliang Nie, Maziar Sanjabi, Hamed Firooz, Xiang Ren

Energy-based Unknown Intent Detection with Data Manipulation (2021.findings-acl)

Challenge:	Explanation regularization (ER) aims to improve NLM generalization by pushing the NLM’s machine rationales to align with human rationale.
Approach:	They propose a framework for evaluating ER models’ OOD generalization along three dimensions: unseen datasets, contrast set tests, and functional tests.
Outcome:	The proposed framework evaluates ER models’ OOD generalization across unseen datasets, contrast set tests, and functional tests.

Copied to clipboard

Yawen Ouyang, Jiasheng Ye, Yu Chen, Xinyu Dai, Shujian Huang, Jiajun Chen

Sentiment Analysis

Challenge:	Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set.
Approach:	They propose a framework to generate high-quality OOD utterances with importance weighTs (GOT) their framework is fine-tuned to detect out-of-distribution utterrances .
Outcome:	The proposed framework can achieve state-of-the-art results on two benchmark datasets.

Debiasing Multimodal Models via Causal Information Minimization (2023.findings-emnlp)

Copied to clipboard

Vaidehi Patil, Adyasha Maharana, Mohit Bansal

Out-of-Distribution Generalization in Natural Language Processing: Past, Present, and Future (2023.emnlp-main)

Challenge:	Existing methods for debiasing multimodal models use approximate heuristics to represent the biases, such as shallow features from early stages of training or unimodal features for multimodal tasks like VQA, which may not be accurate.
Approach:	They propose a method that leverages causally-motivated information minimization to learn the confounder representations of a causal graph for multimodal data.
Outcome:	The proposed method improves out-of-distribution performance on multiple multimodal datasets without sacrificing in-distance performance.

Copied to clipboard

Linyi Yang, Yaoxian Song, Xuan Ren, Chenyang Lyu, Yidong Wang, Jingming Zhuo, Lingqiao Liu, Jindong Wang, Jennifer Foster, Yue Zhang

Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection (2026.findings-eacl)

Challenge:	Existing literature on the generalization of machine learning models to out-of-distribution data is lacking.
Approach:	They propose to present the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.
Outcome:	The proposed survey provides the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.

Copied to clipboard

Joe Stacey, Lisa Alazraki, Aran Ubhi, Beyza Ermis, Aaron Mueller, Marek Rei

A Critical Analysis of Document Out-of-Distribution Detection (2023.findings-emnlp)

Challenge:	Existing methods to improve robustness require changing the fine-tuning process or large-scale data augmentation, which are infeasible or cost prohibitive for closed-source models.
Approach:	They propose to prioritize more complex examples or replace existing training examples with LLM-generated data to improve performance on OOD NLI datasets.
Outcome:	The proposed methods improve performance on difficult OOD datasets while training with synthetic data leads to substantial improvements on easier OOD data.

Copied to clipboard

Jiuxiang Gu, Yifei Ming, Yi Zhou, Jason Kuen, Vlad Morariu, Handong Zhao, Ruiyi Zhang, Nikolaos Barmpalios, Anqi Liu, Yixuan Li, Tong Sun, Ani Nenkova

Teaching Small Language Models Reasoning through Counterfactual Distillation (2024.emnlp-main)

Challenge:	Existing document understanding models focus on single-modal inputs such as images or texts.
Approach:	They propose to use a spatial-aware adapter to adapt transformer-based language models to document domain to exploit multi-modal information.
Outcome:	The proposed model significantly improves the OOD detection performance compared to using a standard language model and to competitive baselines.

Copied to clipboard

Tao Feng, Yicheng Li, Li Chenglin, Hao Chen, Fei Yu, Yin Zhang

Generative-to-Discriminative Test-Time Adaptation via Manifold-Aware Diffusion and Bayesian Distillation (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated remarkable performance in a wide range of downstream tasks.
Approach:	They propose a counterfactual distillation framework that leverages LLMs to generate high-quality counterfacts and utilizes multi-view CoT to enhance the diversity of reasoning samples.
Outcome:	The proposed framework enhances reasoning capabilities of large language models and is more robust to OOD data.

Copied to clipboard

Boyun Zhang, Zequn Xie, Fangming Feng, Zihan Zhang, Yongbo He, Chuxin Wang, Sihang Cai, Tao Jin, Qifei Zhang

Can Large Language Models Learn Independent Causal Mechanisms? (2024.emnlp-main)

Challenge:	Existing discriminative approaches suffer from "confident but wrong" failure mode, blindly adapting to OOD noise leading to error accumulation.
Approach:	They propose a TTA framework that harmonizes the robustness of generative diffusion models with the efficiency of discriminative regression networks via Bayesian Diffusion Distillation (BDD).
Outcome:	The proposed framework reduces MAE from 0.6872 to 0.5673 and boosts binary accuracy by 5.81 percentage points (reaching 57.33%) it also reduces the MAE of the MOSI to SIMS shift and achieves an 11.18-point gain over the baseline.

Copied to clipboard

Gael Gendron, Bao Nguyen, Alex Peng, Michael Witbrock, Gillian Dobbie

Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP (2023.findings-emnlp)

Challenge:	Large Language Models (LLMs) perform poorly on complex reasoning tasks, such as abstract, causal, or logical reasoning.
Approach:	They propose to use two concepts from causality to learn ICMs within LLMs to improve out-of-distribution performance on abstract and causal reasoning tasks.
Outcome:	The proposed model outperforms existing models on abstract and causal reasoning tasks and is more robust to fine-tuning.

Copied to clipboard

Hyuhng Kim, Hyunsoo Cho, Sang-Woo Lee, Junyeob Kim, Choonghyun Park, Sang-goo Lee, Kang Yoo, Taeuk Kim

Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text (2023.acl-long)

Challenge:	Despite advances in computer vision, its application on language input still needs to be explored despite its feasibility.
Approach:	They propose a universal domain adaptation (uniDA) benchmark for natural language that offers thorough viewpoints of the model’s generalizability and robustness.
Outcome:	The proposed model can handle spoken language in the real world while also detecting unprocessable inputs from the target domain.

Copied to clipboard

Qianhui Wu, Huiqiang Jiang, Haonan Yin, Börje Karlsson, Chin-Yew Lin

Large Language and Reasoning Models are Shallow Disjunctive Reasoners (2025.acl-long)

Challenge:	Self-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-difference (ID) examples.
Approach:	They propose a method that integrates strengths and weaknesses of both methods . they use a fine-tuned model as the teacher to teach a randomly initialized student model .
Outcome:	The proposed method outperforms human evaluators in the pair-expert task on the Human ChatGPT Comparison Corpus.

Copied to clipboard

Irtaza Khalid, Amir Masoud Nourollah, Steven Schockaert

Reasoning

Challenge:	Large Language Models (LLMs) struggle with systematic reasoning on out-of-distribution (OOD) tasks.
Approach:	They propose to use a set of constraints to measure OOD generalization to create large reasoning models that can be leveraged to solve real-world problems.
Outcome:	The proposed models outperform their LLM counterparts in single-path reasoning tasks but struggle in multi-path setting.

Curriculum Debiasing: Toward Robust Parameter-Efficient Fine-Tuning Against Dataset Biases (2025.acl-long)

Copied to clipboard

Mingyu Lee, Yeachan Kim, Wing-Lam Mok, SangKeun Lee

CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models (2025.emnlp-main)

Challenge:	Parameter-efficient fine-tuning (PEFT) addresses the memory footprint issue of full fine- tuning by modifying only a subset of model parameters.
Approach:	They propose a framework that debiases models in a biased-to-unbiased order and uses only a subset of parameters to modify model parameters.
Outcome:	The proposed framework accelerates convergence on unbiased examples by approximately twofold and improves ID and OOD performance by 1.2% and 8.0%, respectively.

Copied to clipboard

Kairong Han, Wenshuo Zhao, Ziyu Zhao, Ye Jun Jian, Lujia Pan, Kun Kuang

DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation (2022.acl-long)

Challenge:	Existing fine-tuning paradigms focus on aligning LLMs with task-specific objectives.
Approach:	They propose a pipeline that leverages human priors to automatically generate token-level causal signals and introduce the Re-Attention mechanism to guide training.
Outcome:	The proposed pipeline achieves an average improvement of 5.76% on the STG dataset and 1.56% on downstream tasks.

Copied to clipboard

Nitay Calderon, Eyal Ben-David, Amir Feder, Roi Reichart

Low-Resource NLP

Challenge:	Existing domain adaptation (DA) algorithms are not able to handle out-of-distribution examples due to the costly and labor-intensive data labeling process.
Approach:	They propose a controllable generation approach to deal with domain adaptation challenge by generating a domain-counterfactual textual example from an input text.
Outcome:	The proposed approach outperforms baselines and improves accuracy of state-of-the-art unsupervised DA algorithm.

Leveraging Synthetic Targets for Machine Translation (2023.findings-acl)

Copied to clipboard

Sarthak Mittal, Oleksii Hrinchuk, Oleksii Kuchaiev

Machine Translation

Challenge:	Using synthetic target data, training models on synthetic targets outperforms training on actual ground-truth data.
Approach:	They propose a recipe for training machine translation models on synthetic target data by leveraging a large pre-trained model.
Outcome:	The proposed model outperforms training on real-world translation datasets.

PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning (2024.acl-long)

Copied to clipboard

Xiaoqi Qiu, Yongjie Wang, Xu Guo, Zhiwei Zeng, Yu Yue, Yuhong Feng, Chunyan Miao

BOLT: Benchmarking Open-World Learning for Text Classification (2026.findings-acl)

Challenge:	Recent research shows that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information.
Approach:	They propose to use contrastive learning to promote global feature alignment and learning counterfactual clues to improve model performance.
Outcome:	The proposed method outperforms the state-of-the-art on out-of distribution (OOD) datasets.

Copied to clipboard

Chuan Qin, Xi Chen, Jinpeng Li, Hengshu Zhu

Information Extraction & Text Mining

Challenge:	Existing benchmarks focus on out-of-distribution (OOD) detection while overlooking broader challenges such as the discovery of novel categories.
Approach:	They propose a unified Benchmark and evaluation toolkit supporting Open-world learning for text classification.
Outcome:	The proposed methods overfit training distributions and struggle to generalize to unseen classes.

SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank (2023.findings-emnlp)

Copied to clipboard

Dheeraj Mekala, Adithya Samavedhi, Chengyu Dong, Jingbo Shang

Information Extraction & Text Mining

Challenge:	Existing methods for supervised OOD detection require expensive manual annotation of in-distribution and OOD samples.
Approach:	They propose a self-supervised OOD detection method that requires only in-distribution samples as supervision.
Outcome:	Experiments with multiple classifiers on coarse- and fine-grained datasets show the proposed method performs well in both coarse-and fine-grid settings.

Distance-aware Calibration for Pre-trained Language Models (2024.findings-emnlp)

Copied to clipboard

Alberto Gasparin, Gianluca Detommaso

Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression (2024.findings-emnlp)

Challenge:	Language Models often produce overconfident predictions for both in-distribution and out-of-difference samples, i.e., the model’s output probabilities do not match their accuracy.
Approach:	They propose a post-hoc approach that changes the confidence scores of a Language Model by leveraging the distance between new samples and the in-domain training set.
Outcome:	The proposed approach improves in-domain calibration, robustness to different kind of distribution shift and also the model’s ability to detect out-of-distribution samples.

Copied to clipboard

Aryan Gulati, Xingjian Dong, Carlos Hurtado, Sarath Shekkizhar, Swabha Swayamdipta, Antonio Ortega

Text Clustering

Challenge:	Existing methods for detecting out-of-distribution data are computationally complex and storage-intensive.
Approach:	They propose a soft clustering approach for OOD detection based on non-negative kernel regression . their approach greatly reduces computational and space complexities while retaining competitive performance.
Outcome:	The proposed approach outperforms existing methods by up to 4 AUROC points on four benchmarks while retaining competitive performance.

Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance (2020.acl-main)

Copied to clipboard

Prasetya Ajie Utama, Nafise Sadat Moosavi, Iryna Gurevych

Mitigating Spurious Correlation in Natural Language Understanding with Counterfactual Inference (2022.emnlp-main)

Challenge:	Recent studies show that pre-trained language models rely heavily on idiosyncratic biases of datasets.
Approach:	They propose a method which discourages models from exploiting biases while enabling them to receive enough incentive to learn from all the training examples.
Outcome:	The proposed method improves on out-of-distribution datasets while maintaining original in-district accuracy.

Copied to clipboard

Can Udomcharoenchaikit, Wuttikorn Ponwitayarat, Patomporn Payoungkhamdee, Kanruethai Masuk, Weerayut Buaphet, Ekapol Chuangsuwanich, Sarana Nutanong

Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval (2025.emnlp-main)

Challenge:	Existing approaches to debias NLU models rely on superficial patterns to produce correct predictions . lexical overlap and annotation artifacts can be used to make shortcuts .
Approach:	They propose a causal analysis framework to help debias NLU models by defining causal relationships and utilizing counterfactual inference to mitigate bias.
Outcome:	The proposed framework can improve robustness across three NLU tasks while maintaining high in-distribution performance.

Copied to clipboard

Pranjal A Chitale, Bishal Santra, Yashoteja Prabhu, Amit Sharma

Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation (2026.acl-long)

Challenge:	Existing research does not explore key factors such as optimal augmentation scale and the necessity of using large augmentation models.
Approach:	They propose to use LLMs to augment compact dual-encoder models to improve retrieval performance.
Outcome:	The proposed approach improves retrieval performance but its benefits diminish beyond a certain scale even with diverse augmentation strategies.

Copied to clipboard

Hanwen Shen, Ting Ying, Jiajie Lu, Shanshan Wang

The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs (2026.acl-long)

Challenge:	Debiased large language models excel at handling known or low-bias prompts, but fail on unfamiliar and high-biased prompts.
Approach:	They propose a debiasing framework that detects high-bias prompts and triggers context-aware LoRA updates only when a bias-risk score exceeds a threshold.
Outcome:	The proposed framework reduces toxicity/bias score with significantly lower latency than standard optimization methods.

Copied to clipboard

Zihan Chen, Yiming Zhang, Wenxiang Geng, Zenghui Ding, Yining Sun

Reasoning

Challenge:	Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) exhibit a critical failure mode: they exhibit brittle reasoning capabilities on out-of-distribution tasks.
Approach:	They propose a framework bridging Structural Causal Models and the Information Bottleneck principle to explain this paradox.
Outcome:	The proposed framework bridges the framework between SCM and IB principles to explain the problem.

Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation (2026.findings-acl)

Copied to clipboard

Jinwen Chen, Hainan Zhang, Liang Pang, Yongxin Tong, Haibo Zhou, Wei Lin, Zhiming Zheng

Semantic Role Labeling Guided Out-of-distribution Detection (2024.lrec-main)

Challenge:	Existing RAG systems require uploading local documents to the cloud, resulting in inference latency and poor generalization on out-of-distribution (OOD) inputs.
Approach:	They propose a generalizable knowledge-distilled parametric RAG model aligned with standard RAG in document structure and parameter activation.
Outcome:	The proposed model outperforms baselines in accuracy and generalizes well on out-of-distribution (OOD) data.

Copied to clipboard

Jinan Zou, Maihao Guo, Yu Tian, Yuhao Lin, Haiyao Cao, Lingqiao Liu, Ehsan Abbasnejad, Javen Qinfeng Shi

False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize (2026.findings-acl)

Challenge:	Existing methods for identifying domain-shifted instances are prone to OOD and adversarial inputs.
Approach:	They propose an unsupervised method that separates, extracts, and learns the semantic role labeling guided out-of-distribution Detection (SRLOOD) they propose a self-supervised approach to enhance global-local feature learning by predicting SRL extracted role.
Outcome:	The proposed method achieves SOTA performance on four OOD benchmarks.

Copied to clipboard

Cheng Wang, Zeming Wei, Qin Liu, Wenxuan Zhou, Muhao Chen