MODEL-AGNOSTIC

Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models (2025.naacl-short)

Challenge:	Existing methods to optimize prompts rely on LLMs' self-generation ability but lack interpretability due to implicit optimization.
Approach:	They propose a model-agnostic prompt quality merits and a merit-guided, locally deployable prompt optimizer trained on a lightweight LLM to improve prompt quality.
Outcome:	The proposed model avoids online optimization, reduces privacy concerns, and generalizes effectively to both large-scale and lightweight inference models.

Copied to clipboard

Sangmin Woo, Kang Zhou, Yun Zhou, Shuai Wang, Sheng Guan, Haibo Ding, Lin Lee Cheong

SAJA: A Simple Approach to Judge Alignment for LLM-as-a-Judge (2026.acl-industry)

Challenge:	Existing methods to mitigate object hallucination are impractical for proprietary LVLMs.
Approach:	They propose a framework to identify optimal visual prompts that enhance LVLM responses without access to model internals.
Outcome:	The proposed approach is model-agnostic and can be used on open-source and proprietary LVLMs.

Copied to clipboard

Sneha Kola, Pankaj Kumar Sharma, Soumyadeep Dey, Bamdev Mishra, Mayur Datar

GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation (2025.findings-emnlp)

Challenge:	Current approaches to evaluate text at scale require multiple calls and per-dataset prompt tuning.
Approach:	They propose a model-agnostic approach to evaluate judge alignment that uses a lightweight calibration head.
Outcome:	a new model with SAJA matches more complex systems across four evaluation paradigms . it outperforms uncalibrated models on MT-Bench pairwise preference and competitive performance on five classification benchmarks compared to uncalibred models .

Copied to clipboard

Wen Ye, Zhaocheng Liu, Gui Yuwei, Tingyu Yuan, Yunyue Su, Bowen Fang, Chaoyang Zhao, Qiang Liu, Liang Wang

Metamo: Empowering Large Language Models with Psychological Distortion Detection for Cognition-aware Coaching (2025.emnlp-demos)

Challenge:	Existing methods for text-to-image synthesis lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness.
Approach:	They propose a plug-and-play multi-agent system called GenPilot that integrates error analysis, clustering-based adaptive exploration, fine-grained verification and a memory module for iterative optimization.
Outcome:	The proposed method improves text consistency and structural coherence on images with a plug-and-play system.

Copied to clipboard

Hajime Hotta, Huu-Loi Le, Manh-Cuong Phan, Minh-Tien Nguyen

Flexible Weight Tuning and Weight Fusion Strategies for Continual Named Entity Recognition (2024.findings-acl)

Challenge:	Metamo is a browser-based dialogue system that transforms an off-the-shelf large language model into an empathetic coach for everyday workplace concerns.
Approach:	They propose a browser-based dialogue system that first identifies the cognitive distortion behind an emotion, then recognizes the user’s emotion, and finally produces a question-centered reply that invites reflection.
Outcome:	Empirical tests on public corpora showed that the proposed system improved emotionrecognition quality and response diversity without sacrificing latency.

Copied to clipboard

Yahan Yu, Duzhen Zhang, Xiuyi Chen, Chenhui Chu

Black-box language model explanation by context length probing (2023.acl-short)

Challenge:	Existing methods for Named Entity Recognition (CNER) use knowledge distillation to retain old knowledge, but they are too expensive and fail to integrate with existing state-of-the-art models.
Approach:	They propose a weight tuning and weightfusion strategy to learn new entity types while mitigating catastrophic forgetting of old models.
Outcome:	The proposed strategies improve the performance of existing models and are model-agnostic.

Copied to clipboard

Ondřej Cífka, Antoine Liutkus

Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation (2021.eacl-main)

Challenge:	context length probing is a new explanation technique for large language models . it tracks the predictions of a model as a function of the length of available context .
Approach:	They propose a method that tracks the predictions of a model as a function of the length of available context and allows to assign differential importance scores to different contexts.
Outcome:	The proposed method is model-agnostic and does not rely on access to model internals beyond token-level probabilities.

Copied to clipboard

Wanrong Zhu, Xin Wang, Tsu-Jui Fu, An Yan, Pradyumna Narayana, Kazoo Sone, Sugato Basu, William Yang Wang

Multimodality

Challenge:	Outdoor vision-and-language navigation (VLN) tasks require visual grounding to generate correct actions.
Approach:	They propose a multimodal text style transfer learning approach to mitigate data scarcity in outdoor vision-and-language navigation tasks.
Outcome:	The proposed approach outperforms baseline models on the outdoor vision-and-language navigation task, improving task completion rate by 8.7% relative to the baseline models.

NeighXLM: Enhancing Cross-Lingual Transfer in Low-Resource Languages via Neighbor-Augmented Contrastive Pretraining (2025.findings-emnlp)

Copied to clipboard

Sicheng Wang, Wenyi Wu, Zibo Zhang

Few Clean Instances Help Denoising Distant Supervision (2022.coling-1)

Challenge:	NeighXLM is a neighbor-augmented contrastive pretraining framework . it exploits intra-language semantic relationships captured during pretraining to construct high-quality positive pairs.
Approach:	They propose a neighbor-augmented contrastive pretraining framework that mines semantic neighbors from unlabeled corpora to enrich target-language supervision.
Outcome:	The proposed framework enriches target-language supervision by mining semantic neighbors from unlabeled corpora.

Copied to clipboard

Yufang Liu, Ziyin Huang, Yijun Wang, Changzhi Sun, Man Lan, Yuanbin Wu, Xiaofeng Mou, Ding Wang

Challenge:	Existing distantly supervised entity relation extractors rely on noisy data for training and evaluation.
Approach:	They propose a criterion for clean instance selection based on influence functions to collect sample-level evidence for recognizing good instances.
Outcome:	The proposed method shows strong performance on real and synthetic noisy datasets.

Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis (2022.naacl-main)

Copied to clipboard

Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi

Information Extraction & Text Mining

Challenge:	Existing studies rely on entity information for sentence-level relation extraction (RE) but this can leak superficial and spurious clues of relations.
Approach:	They propose to use entity mentions to extract relations from textual context . they use a causal graph to model dependencies between variables in RE models .
Outcome:	The proposed method yields significant gains on both effectiveness and generalization for RE.

Hierarchical Pre-training for Sequence Labelling in Spoken Dialog (2020.findings-emnlp)

Copied to clipboard

Emile Chapuis, Pierre Colombo, Matteo Manica, Matthieu Labeau, Chloé Clavel

Dialogue Systems & Conversational Agents

Challenge:	Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems.
Approach:	They propose a new approach to learn generic representations adapted to spoken dialog using a hierarchical encoder based on transformer architectures.
Outcome:	The proposed model is model-agnostic and contains 10 datasets of various sizes.

MorphMark: Flexible Adaptive Watermarking for Large Language Models (2025.acl-long)

Copied to clipboard

Zongqi Wang, Tianle Gu, Baoyuan Wu, Yujiu Yang

Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph (2024.acl-long)

Challenge:	Existing methods for tracing text origins struggle with a watermark effectiveness dilemma . weaker watermarks preserve text quality, while stronger ones enhance effectiveness .
Approach:	They propose a method that adjusts watermark strength in response to changes in a key factor . they first formalize the problem within a multi-objective trade-off analysis framework .
Outcome:	The proposed method improves watermark effectiveness but reduces text quality . the proposed method prioritizes flexibility and time and space efficiency .

Copied to clipboard

Xiaochen Gao, Feng Yao, Kewen Zhao, Beilei He, Animesh Kumar, Vish Krishnan, Jingbo Shang

UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models (2025.emnlp-main)

Challenge:	Scaling up language models has demonstrated predictable improvement and unprecedented abilities in many language tasks.
Approach:	They propose a fine-grained cLAim depeNdency graph that captures the dependencies within the patent data and extends the embedding-based state-of-the-art (SOTA) they then explore prompt-based methods to harness proprietary LLMs' potential, but find the best results close to random guessing, underlining the ineffectiveness of model scaling-up.
Outcome:	The proposed graph methods outperform the standard model scaling methods in the patent approval prediction task and show that they are cost-effective.

Copied to clipboard

Roman Vashurin, Maiya Goloburda, Preslav Nakov, Maxim Panov

Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) generate misleading or outright incorrect information.
Approach:	They propose a method that debiases uncertainty scores on output length and uses residuals as corrected, length-invariant estimates.
Outcome:	The proposed method improves over nominally length-normalized methods on machine translation, summarization, and question-answering tasks.

Copied to clipboard

Peiyi Wang, Yifan Song, Tianyu Liu, Binghuai Lin, Yunbo Cao, Sujian Li, Zhifang Sui

Robustness in NLP

Challenge:	Existing studies attribute catastrophic forgetting to the corruption of the learned representations as new relations come . Continual relation extraction models suffer from catastrophic forgetting when learning new relations .
Approach:	They propose to use adversarial class augmentation mechanism to learn more precise representations . they propose to train the model on a sequence of tasks where two new relations are discovered .
Outcome:	The proposed model improves on two popular benchmarks.

Label-Efficient Model Selection for Text Generation (2024.acl-long)

Copied to clipboard

Shir Ashury Tahan, Ariel Gera, Benjamin Sznajder, Leshem Choshen, Liat Ein-Dor, Eyal Shnarch

Beyond Layout Embedding: Layout Attention with Gaussian Biases for Structured Document Understanding (2023.findings-emnlp)

Challenge:	Model selection for a given task can entail extensive annotation of the quality of outputs of different models.
Approach:	They propose a model-agnostic method to make an informed decision between candidate text generation models based on preference annotations.
Outcome:	The proposed method reduces the required number of annotations by up to 75% while maintaining high evaluation reliability.

Copied to clipboard

Xi Zhu, Xue Han, Shuyuan Peng, Shuo Lei, Chao Deng, Junlan Feng

Representation Learning

Challenge:	Existing methods for encoding layout information rely on millions of learnable parameters . polar coordinates provide superior choice for layout modeling, study finds .
Approach:	They propose to model layout attention with Gaussian biases by feeding polar coordinates into 2-D Gausssian kernels.
Outcome:	The proposed model improves on three widely used benchmarks.

Human-grounded Evaluations of Explanation Methods for Text Classification (D19-1)

Copied to clipboard

Piyawat Lertvittayakumjorn, Francesca Toni

Explainability & Interpretability in NLP

Challenge:	Explainable Artificial Intelligence (XAI) is aimed at providing explanations for decisions made by AI systems.
Approach:	They propose to use model-agnostic and model-specific explanation methods for CNNs for text classification to provide human-grounded evaluations.
Outcome:	The proposed methods could be used to explain models' results and improve AIs and humans in many cases.

Disentangling Transformer Language Models as Superposed Topic Models (2023.emnlp-main)

Copied to clipboard

Jia Peng Lim, Hady Lauw

Explainability & Interpretability in NLP

Challenge:	Topic Modelling is an established area of research where the quality of a given topic is measured using coherence metrics.
Approach:	They propose a weight-based approach to search and disentangle decoder-only TLM by a Wikipedia corpus.
Outcome:	The proposed approach can be applied to GPT-2 models and LLaMA models.

A Model-agnostic Data Manipulation Method for Persona-based Dialogue Generation (2022.acl-long)

Copied to clipboard

Yu Cao, Wei Bi, Meng Fang, Shuming Shi, Dacheng Tao

Dialogue Systems & Conversational Agents

Challenge:	Existing models for introducing explicit personas are expensive due to their expensive collection costs.
Approach:	They propose a data manipulation method which is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.
Outcome:	The proposed method is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.

HARP: Hesitation-Aware Reframing in Transformer Inference Pass (2025.naacl-long)

Copied to clipboard

Romain Storaï, Seung-won Hwang

Good-Enough Compositional Data Augmentation (2020.acl-main)

Challenge:	a recent study has shown that inference steps are not equally challenging, with some being "harder" and others "easier."
Approach:	They propose a modified Transformer forward pass that selectively applies additional computation when the model encounters uncertainty during token generation.
Outcome:	The proposed method achieves performance gains while maintaining inference times twice faster than beam search.

Copied to clipboard

Jacob Andreas

Interpreting Topic Models in Byte-Pair Encoding Space (2025.coling-main)

Challenge:	a proposed data augmentation protocol provides a compositional inductive bias in conditional and unconditional sequence models.
Approach:	They propose a data augmentation protocol that provides a compositional inductive bias in conditional and unconditional sequence models by replacing discontinuous fragments with other fragments that appear in at least one similar environment.
Outcome:	The proposed protocol reduces error rate by 87% on diagnostic tasks and 16% on semantic parsing tasks.

Copied to clipboard

Jia Peng Lim, Hady Lauw

Explainability & Interpretability in NLP

Challenge:	Byte-pair encoding (BPE) is a popular method of tokenizing valid words onto a token space V b with a predetermined fixed size, and handling out-of-vocabulary words, breaking words into smaller tokens.
Approach:	They propose to interpret the recovery of valid words from these tokens as a ranking problem and apply existing evaluation measures to topic sets.
Outcome:	The proposed model interprets the recovery of valid words from these tokens as a ranking problem and applies existing evaluation measures.

Textual Dataset Distillation via Language Model Embedding (2024.findings-emnlp)

Copied to clipboard

Yefan Tao, Luyang Kong, Andrey Kan, Laurent Callot

A Universal Avoidance Method for Diverse Multi-branch Generation (2026.findings-acl)

Challenge:	prevailing methods for dataset distillation generate distilled data as embedding vectors, which are not human-readable.
Approach:	They propose a model-agnostic, data-efficient method that leverages Language Model embeddings . their method offers enhanced flexibility and improved transferability .
Outcome:	The proposed method achieves comparable performance with faster processing times compared to other methods . it offers enhanced flexibility and improved transferability, expanding the range of potential applications .

Copied to clipboard

Kyeongman Park, Minha Jhang, Kyomin Jung

Challenge:	generative models still lack human-level creativity, especially in multi-branch diversity tasks.
Approach:	They propose a model-agnostic and computationally efficient generation strategy that penalizes similarity among previously generated outputs.
Outcome:	The proposed method achieves 1.9 times higher diversity, runs 4.4 times faster, and requires only 1/64 of the FLOPs compared to state-of-the-art methods.

System Combination via Quality Estimation for Grammatical Error Correction (2023.emnlp-main)

Copied to clipboard

Muhammad Reza Qorib, Hwee Tou Ng

Syntactic Text Processing

Challenge:	Existing quality estimation models are not good enough to distinguish good corrections from bad ones, resulting in low F0.5 scores when used for system combination.
Approach:	They propose a new quality estimation model that gives a better estimate of the quality of a corrected sentence.
Outcome:	The proposed model outperforms the state-of-the-art on the CoNLL-2014 and BEA-2019 test sets, and achieves the highest F0.5 scores published to date.

Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models (2024.emnlp-main)

Copied to clipboard

Minghao Wu, Thuy-Trang Vu, Lizhen Qu, Reza Haf

BiasFilter: An Inference-Time Debiasing Framework for Large Language Models (2025.findings-emnlp)

Challenge:	Large language models are fine-tuned on diverse datasets to develop a range of skills . each skill has unique characteristics, and datasets are heterogeneous and imbalanced . a general, model-agnostic, reinforcement learning framework is proposed to optimize data usage .
Approach:	They propose a general, model-agnostic, reinforcement learning framework that optimizes data usage automatically during the fine-tuning process.
Outcome:	The proposed framework optimizes data usage automatically during the fine-tuning process.

Copied to clipboard

Xiaoqing Cheng, Ruizhe Chen, Hongying Zan, Yuxiang Jia, Min Peng

Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level (2024.emnlp-main)

Challenge:	Existing methods for debiasing large language models incur high human and computational costs and are limited in their effectiveness.
Approach:	They propose a model-agnostic, inference-time debiasing framework that enforces fairness by filtering generation outputs in real time.
Outcome:	The proposed framework mitigates social bias across a range of LLMs while preserving overall generation quality.

Copied to clipboard

Zhaopeng Feng, Ruizhe Chen, Yan Zhang, Zijie Meng, Zuozhu Liu

Machine Translation

Challenge:	General-purpose Large Language Models (LLMs) like GPT-4 have exhibited strong translation abilities.
Approach:	They propose to use a model-agnostic model to refine the performance of general-purpose large-language models for machine translation (MT) by utilizing Gemma-2B/7B as the backbone.
Outcome:	The proposed model-agnostic and cost-effective tool improves the performance of general-purpose large-language models for machine translation (MT) by integrating it with any general-use LLM.

GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models (2025.emnlp-main)

Copied to clipboard

Dylan Hutson, Daniel Vennemeyer, Aneesh Deshmukh, Justin Zhan, Tianyu Jiang

Retrieval-augmented GUI Agents with Generative Guidelines (2025.emnlp-main)

Challenge:	Large language models excel at factual recall, arithmetic reasoning, multi-turn dialogue . their capacity as askers, formulating strategic, adaptive, and information-seeking questions, remains less explored .
Approach:	They propose a protocol for evaluating large language models as strategic question-askers . they propose entropy-based methods that filter candidates via ConceptNet and Bayesian method that tracks belief updates over semantic concepts .
Outcome:	The proposed method is model-agnostic and supports post hoc analysis.

Copied to clipboard

Ran Xu, Kaixin Ma, Wenhao Yu, Hongming Zhang, Joyce C. Ho, Carl Yang, Dong Yu

Information Retrieval

Challenge:	GUI agents powered by vision-language models struggle with real-world tasks due to their complex nature and limited training data.
Approach:	They propose a lightweight vision-language model that leverages web tutorials at inferencetime to synthesize GUI agents.
Outcome:	The proposed agent outperforms baseline GUI agents and surpasses other inference baselines by 2.6% to 13.3% across two model sizes.

Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents (2025.findings-emnlp)

Copied to clipboard

Shouju Wang, Fenglin Yu, Xirui Liu, Xiaoting Qin, Jue Zhang, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan

Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal Chinese Spelling Correction (2024.lrec-main)

Challenge:	Existing benchmarks for privacy performance of LLM agents are limited to static, simplified scenarios.
Approach:	They propose a model-agnostic, contextual integrity based mitigation approach that effectively reduces privacy leakage from 36.08% to 7.30% on DeepSeek-R1 and from 33.06% to 8.32% on GPT-4o.
Outcome:	The proposed approach reduces privacy leakage from 36.08% to 7.30% on DeepSeek-R1 and from 33.06% to 8.32% on GPT-4o while preserving task helpfulness.

Copied to clipboard

Yongliang Lin, Zhen Zhang, Mengting Hu, Yufei Sun, Yuzhi Zhang

Multimodality

Challenge:	Chinese spelling correction (CSC) aims to detect and correct spelling errors in Chinese texts.
Approach:	They propose a framework that incorporates uncertainty into feature learning and correction stages . they propose to combine the uncertainty of multimodal features with model learning .
Outcome:	The proposed framework improves on three public datasets.

Model-Agnostic Cross-Lingual Training for Discourse Representation Structure Parsing (2024.lrec-main)

Copied to clipboard

Jiangming Liu

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving (2025.emnlp-main)

Challenge:	Discourse Representation Structure (DRS) parsers are constrained when trained exclusively on monolingual data.
Approach:	They propose a cross-lingual training strategy that leverages cross-linguistic training data to train models in multiple languages.
Outcome:	The proposed method improves clause and graph parsing in English, German, Italian and Dutch.

Copied to clipboard

Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost, Chitta Baral, Chen-Yu Lee, Tomas Pfister, Hamid Palangi

Reasoning

Challenge:	Existing methods for natural planning lack constraint-guided iterative verification and adaptive selection . a recent study found that LLMs are not good at such planning.
Approach:	They propose a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents.
Outcome:	The proposed framework improves inference-time algorithms on NATURAL PLAN and OlympiadBench benchmarks.

Opinions Are Not Always Positive: Debiasing Opinion Summarization with Model-Specific and Model-Agnostic Methods (2024.lrec-main)

Copied to clipboard

Yanyue Zhang, Yilong Lai, Zhenglin Wang, Pengfei Li, Deyu Zhou, Yulan He

Sentiment Analysis

Challenge:	Existing opinion summarization frameworks are reluctant to generate negative summaries given input of negative opinions.
Approach:	They propose to disentangle input into sentiment-relevant and sentiment-irrelevant components through adversarial loss.
Outcome:	The proposed approaches reduce sentiment bias in the existing opinion summarization dataset . the proposed approaches generate better summaries with a more balanced emotional polarity distribution .

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models (2025.findings-emnlp)

Copied to clipboard

Zicong Tang, Ziyang Ma, Suqing Wang, Zuchao Li, Lefei Zhang, Hai Zhao, Yun Li, Qianren Wang

Visual Data in NLP

Challenge:	Existing methods to prune redundant vision tokens struggle in shallow layers due to the lack of contextual information.
Approach:	They propose a layer-wise contextualized visual token pruning method that uses a plug-and-play Pruning Module to prune redundant vision tokens.
Outcome:	The proposed method outperforms training-free pruning methods under equal token budgets and surpasses training based methods with comparable supervision.

Semi-Supervised Diseased Detection from Speech Dialogues with Multi-Level Data Modeling (2026.findings-acl)

Copied to clipboard

Xingyuan Li, Mengyue Wu

Attention Basin: Why Contextual Position Matters in Large Language Models (2026.acl-long)

Challenge:	Existing methods for learning from weakly-supervised speech data are hampered by severe data scarcity and the subjective nature of clinical annotations.
Approach:	They propose a framework that explicitly models pathological traits by jointly learning from frame-level, segment-level and session-level representations within unsegmented clinical dialogues.
Outcome:	The proposed framework is model-agnostic, robust across languages and conditions, and highly data-efficient.

Copied to clipboard

Zihao Yi, Zhenqing Ling, Delong Zeng, Haohao Luo, Zhe Xu, Wei Liu, Jian Luan, Wanxia Cao, Ying Shen

HG-InsightLog: Context Prioritization and Reduction for Question Answering with Non-Natural Language Construct Log Data (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are sensitive to the contextual position of information in input.
Approach:	They introduce Attention-Driven Reranking (AttnRank) which estimates a model’s intrinsic positional attention preferences using a small calibration set and reorders retrieved documents or few-shot examples to align the most salient content with these high-attention positions.
Outcome:	Experiments on multi-hop QA and few-shot in-context learning tasks show that AttnRank achieves substantial improvements across 10 large language models of varying architectures and scales, without modifying model parameters or training procedures.

Copied to clipboard

Supriya Bajpai, Athira Gopal, Chandrakant Harjpal, Niraj Kumar

Question Answering

Challenge:	Log files are crucial for monitoring, diagnostics, and root cause analysis in IT systems . their sheer volume makes manual analysis overwhelming and traditional methods are ineffective .
Approach:	They propose a framework that constructs a multi-entity temporal hypergraph using log attribute-value pairs as nodes and connects them with hyperedges.
Outcome:	The proposed framework is model-agnostic and training-free and scales with open-source LLMs.

Safety Sidecar: Reflection-Driven Runtime Control for Safer Agents (2026.findings-acl)

Copied to clipboard

Wang Bin, Quan Jiazheng, Xingrui Yu, Hu Hansen, Yu Hao, Anjun Gao, Zhenglin Wan, Hui LI, Ivor Tsang