MODEL FINE-TUNING

Zero-Shot Strategies for Length-Controllable Summarization (2025.findings-naacl)

Challenge:	Large Language Models (LLMs) generate nonfacts and deviate from desired criteria for text generation.
Approach:	They propose a controlled text generation algorithm that enforces adherence toward specific rhetorical relations in an LLM sentence-completion context by a parser-driven decoding scheme.
Outcome:	The proposed method generates sentences that satisfy desired rhetorical relations in an LLM.

Copied to clipboard

Fabian Retkowski, Alexander Waibel

Building a Family of Data Augmentation Models for Low-cost LLM Fine-tuning on the Cloud (2025.coling-industry)

Challenge:	Large language models struggle with precise length control, particularly in zero-shot settings.
Approach:	They propose to use length approximation, target adjustment, sample filtering and automated revisions to improve LLMs' length control capabilities.
Outcome:	The proposed methods improve length control in large language models while maintaining or enhancing summary quality without the need for model fine-tuning or architectural changes.

Copied to clipboard

Chengyu Wang, Yuanhao Yue, Jun Huang, Peng Wang

Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large Language Model (2024.emnlp-industry)

Challenge:	Existing models for learning large language models are expensive and difficult to build and fine-tune.
Approach:	They propose a family of data augmentation models to improve model fine-tuning efficiency . they leverage powerful LLMs to expand, refine and re-write instructions and responses .
Outcome:	The proposed models improve the efficiency of model fine-tuning by leveraging small datasets and quality assessment techniques.

Copied to clipboard

Subhadip Nandi, Neeraj Agrawal

Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning (2025.emnlp-industry)

Challenge:	Existing approaches to named entity recognition are domain specific and require a domain specific architecture.
Approach:	They propose a retrieval augmented large language model for Named Entity Recognition . the model uses word-embedding over sentence-level embedding to fine tune .
Outcome:	The proposed model outperforms existing models on the CrossNER dataset.

Copied to clipboard

Yajie Li, Albert Galimov, Mitra Datta Ganapaneni, Pujitha Thejaswi, De Meng, Priyanshu Kumar, Saloni Potdar

Predicting Customer Satisfaction with Soft Labels for Ordinal Classification (2023.acl-industry)

Challenge:	Entity Linking (EL) relies on large labeled datasets and extensive fine-tuning . lexical ambiguity, knowledge-intensive cases and low-context mentions are some of the challenges.
Approach:	Entity Linking (EL) relies on large annotated datasets and extensive fine-tuning . authors propose a pipeline that integrates candidate generation, context-based scoring, adaptive routing, and selective reasoning .
Outcome:	ARTER outperforms ReFinED and LLM-based pipelines on standard benchmarks . it performs twice as efficiently on 5 out of 6 datasets and doubles the number of tokens compared to pipelines using LLM .

Copied to clipboard

Etienne Manderscheid, Matthias Lee

Text Classification

Challenge:	a typical call center only responds to 8% of customers with a customer satisfaction survey . a predictive algorithm that infers CSAT on the 1-5 scale is needed to minimize this data sparsity and response bias.
Approach:	They propose an algorithm that infers CSAT on 1-5 scale on inbound calls to the call center . they reframe the problem into a binary class and map it back to five classes .
Outcome:	The proposed model is able to support keycustomer workflows with high accuracy overmillions of calls a month.

Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs (2025.emnlp-industry)

Copied to clipboard

Soham Satyadharma, Fatemeh Sheikholeslami, Swati Kaul, Aziz Umit Batur, Suleiman A. Khan

EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI (2026.findings-acl)

Challenge:	Our system generates and refines prompts for evaluating attribute quality across tens of thousands of product category–attribute pairs.
Approach:	They propose a free cascade for auto-prompting Large Language Models (LLMs) that generates and refines prompts for evaluating attribute quality across tens of thousands of product category–attribute pairs.
Outcome:	The proposed system improves precision and recall by 8–10% over chain-of-thought prompting while reducing domain expert effort from 5.1 hours to 3 minutes per attribute.

Copied to clipboard

Longfei Zuo, Barbara Plank, Siyao Peng

Explainability & Interpretability in NLP

Challenge:	Human label variation (HLV) arises when multiple labels are valid for the same instance.
Approach:	They propose a framework for generating and validating explanations to detect errors using large language models (LLMs) EVADE framework provides broader explanation coverage and requires less human intervention .
Outcome:	The proposed framework provides broader explanation coverage, requires less human intervention, and delivers better downstream performance in predicting label distributions.

A Recipe for Arbitrary Text Style Transfer with Large Language Models (2022.acl-short)

Copied to clipboard

Emily Reif, Daphne Ippolito, Ann Yuan, Andy Coenen, Chris Callison-Burch, Jason Wei

Low-Resource NLP

Challenge:	augmented zero-shot learning is a prompting method that allows large language models to perform zero-shoot text style transfer to arbitrary styles, without any model fine-tuning or exemplars in the target style.
Approach:	They propose a prompting method that frames style transfer as a sentence rewriting task and requires only a natural language instruction.
Outcome:	The proposed method is based on a large language model and is shown to perform on standard style transfer tasks and arbitrary transformations.

Dissecting Human and LLM Preferences (2024.acl-long)

Copied to clipboard

Junlong Li, Fan Zhou, Shichao Sun, Yikai Zhang, Hai Zhao, Pengfei Liu

Boosting Neural Machine Translation with Similar Translations (2020.acl-main)

Challenge:	a recent study shows that human and Large Language Model preferences are important for model fine-tuning and evaluation.
Approach:	They dissect the preferences of human and 32 different Large Language Models to understand their quantitative composition.
Outcome:	The proposed model is compared with 32 different large language models using real-world user-model conversations.

Copied to clipboard

Jitao Xu, Josep Crego, Jean Senellart

Machine Translation

Challenge:	Statistical Machine Translation and fuzzy matching are completely different in their finality.
Approach:	They propose to use fuzzy matching to train neural machine translation to make use of similar translations, in a similar way a human translator employs fuzzy matches.
Outcome:	The proposed methods improve translation accuracy and fine-tuned model for unseen translation pairs.

Cultural Learning-Based Culture Adaptation of Language Models (2025.acl-long)

Copied to clipboard

Chen Cecilia Liu, Anna Korhonen, Iryna Gurevych

SocREval: Large Language Models with the Socratic Method for Reference-free Reasoning Evaluation (2024.findings-naacl)

Challenge:	Existing approaches for adapting large language models to diverse cultural values often rely on prompt engineering.
Approach:	They propose a framework for enhancing LLM alignment with cultural values based on cultural learning that leverages simulated social interactions to generate role-playing scenarios.
Outcome:	The proposed framework improves cultural value alignment across various model architectures measured using World Value Survey data.

Copied to clipboard

Hangfeng He, Hongming Zhang, Dan Roth

PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning (2024.naacl-long)

Challenge:	Existing reference-free reasoning evaluation metrics rely on human-annotated reasoning chains as references, but require fine-tuning with human-derived chains before evaluation.
Approach:	They propose to use GPT-4 to automatically evaluate reasoning chain quality by leveraging the Socratic method.
Outcome:	Empirical results show that the proposed approach significantly improves existing reference-free reasoning evaluation metrics.

Copied to clipboard

Tianrong Zhang, Zhaohan Xi, Ting Wang, Prasenjit Mitra, Jinghui Chen

QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation (2025.emnlp-main)

Challenge:	Existing studies have shown that pre-trained language models can be backdoored such that model behavior is manipulated when trigger tokens are presented.
Approach:	They propose a backdoor mitigation strategy for NLP models via adversarial prompt-tuning in few-shot settings that uses two extra sets of soft tokens which approximate the trigger and counteract it respectively.
Outcome:	The proposed method keeps model parameters intact and only utilizes two extra sets of soft tokens which approximate the trigger and counteract it respectively.

Copied to clipboard

Mengze Hong, Wailing Ng, Chen Jason Zhang, Di Jiang

Challenge:	Existing benchmarks often lack domain coverage and provide limited insights into the working context of Chinese LLMs.
Approach:	They propose a multi-domain Chinese QA benchmark dedicated to localized assessment of Chinese LLMs.
Outcome:	The Qwen2.5 model outperforms the more advanced GPT-4o model in the Chinese market . the dataset includes over 17,000 questions across six vertical domains .

Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach (2024.findings-emnlp)

Copied to clipboard

Dongyue Li, Ziniu Zhang, Lu Wang, Hongyang Zhang

Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning (2025.findings-emnlp)

Challenge:	a new algorithm to estimate fine-tuning performance for a target task is proposed . conventional subset selection methods require repeated training on subsets of auxiliary tasks .
Approach:	They propose an algorithm to fine-tune a language model for a target task by optimally using auxiliary tasks' information.
Outcome:	The proposed method can estimate fine-tuning performance on CPUs in seconds.

Copied to clipboard

Siqu Ou, Hongcheng Liu, Pingjie Wang, Yusheng Liao, Chuan Xuan, Yanfeng Wang, Yu Wang

Multimodality

Challenge:	Existing methods for dynamic spatial reasoning are limited to text or static visual domains .
Approach:	They propose a framework that augments textual reasoning chains with dynamic visual drafts .
Outcome:	The proposed framework outperforms existing methods in dynamic spatial reasoning tasks.

Universal Prompt Optimizer for Safe Text-to-Image Generation (2024.naacl-long)

Copied to clipboard

Zongyu Wu, Hongcheng Gao, Yueze Wang, Xiang Zhang, Suhang Wang

SALTED: A Framework for SAlient Long-tail Translation Error Detection (2022.findings-emnlp)

Challenge:	Existing studies based on image checker, model fine-tuning and embedding blocking are impractical in real-world applications.
Approach:	They propose a novel reward function measuring toxicity and text alignment of generated images and train the optimizer through Proximal Policy Optimization.
Outcome:	The proposed model reduces the likelihood of various models in generating inappropriate images, with no significant impact on text alignment.

Copied to clipboard

Vikas Raunak, Matt Post, Arul Menezes

Machine Translation

Challenge:	Traditional machine translation metrics are insensitive to the long tail of behavioral problems.
Approach:	They propose a specification-based framework for behavioral testing of NMT models . they use high-precision detectors that flag errors between a source sentence and output .
Outcome:	The proposed framework provides a reliable view of problems that were previously invisible.

CERET: Cost-Effective Extrinsic Refinement for Text Generation (2024.naacl-long)

Copied to clipboard

Jason Cai, Hang Su, Monica Sunkara, Igor Shalyminov, Saab Mansour

Text Generation

Challenge:	Large Language Models (LLMs) generate incomplete, biased or misleading outputs in their initial attempts.
Approach:	They propose a method for refining text generation that takes into account semantic stability, entailment and inter-sample uncertainty measures.
Outcome:	The proposed method outperforms self-consistency and self-rerank baselines under various task setups by 1.6% and 3.5% respectively.

Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study (2024.lrec-main)

Copied to clipboard

Peiyu Liu, Zikang Liu, Ze-Feng Gao, Dawei Gao, Wayne Xin Zhao, Yaliang Li, Bolin Ding, Ji-Rong Wen

Bayesian Optimization for Controlled Image Editing via LLMs (2025.findings-acl)

Challenge:	Large Language Models (LLMs) require significant computational resources for deployment and use.
Approach:	They propose to use low-bit quantization methods to reduce memory footprint and increase inference rate to improve performance of Large Language Models.
Outcome:	The proposed methods can reduce the memory footprint and increase the inference rate of LLMs.

Copied to clipboard

Chengkun Cai, Haoliang Liu, Xu Zhao, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, John Lee, Jenq-Neng Hwang, Lei Li

Visual Data in NLP

Challenge:	achieving precise control over generated content and maintaining semantic consistency remain significant limitations, particularly concerning grounding techniques and the necessity for model fine-tuning.
Approach:	They propose an off-the-shelf approach that integrates Large Language Models with Bayesian Optimization to facilitate precise and user-friendly image editing.
Outcome:	The proposed approach outperforms existing methods in editing accuracy and semantic preservation, as validated using different LLMs including Claude3 and GPT-4.

Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech (2021.emnlp-main)

Copied to clipboard

Katrin Tomanek, Vicky Zayats, Dirk Padfield, Kara Vaillancourt, Fadi Biadsy

Speech & Audio in NLP

Challenge:	Automatic Speech Recognition systems perform poorly on atypical speech and heavily accented speech.
Approach:	They add a residual adapter to the encoder layer to improve model adaptation . they show that the residual adapters update only a tiny fraction of the model parameters .
Outcome:	The proposed model fine-tuning improves performance on atypical and accented speech . the system can update only a tiny fraction of the model parameters .

Meta-Task Prompting Elicits Embeddings from Large Language Models (2024.acl-long)

Copied to clipboard

Yibin Lei, Di Wu, Tianyi Zhou, Tao Shen, Yu Cao, Chongyang Tao, Andrew Yates

Enhancing Cross Text-Molecule Learning by Self-Augmentation (2024.findings-acl)

Challenge:	Existing methods for large language modeling are based on task-related instructions or prompts.
Approach:	They propose a method for generating high-quality sentence embeddings from Large Language Models (LLMs) using meta-task prompts.
Outcome:	The proposed method produces high-quality sentences without fine-tuning . it excels on STS benchmarks and in downstream tasks, surpassing models with similar prompts .

Copied to clipboard

Yinuo Jiang, Xiang Zhuang, Keyan Ding, Qiang Zhang, Huajun Chen

Few-Shot Learning with Siamese Networks and Label Tuning (2022.acl-long)

Challenge:	Existing datasets are limited due to the difficulty of collecting precise molecule-description pairs. Existing approaches to enhance large language models include a data augmentation framework and a new dataset called SAPubChem-41.
Approach:	They propose a framework that interweaves model fine-tuning and data augmentation to overcome the scarcity of high-quality labeled data.
Outcome:	The proposed framework interweaves model fine-tuning and data augmentation to overcome the scarcity of high-quality labeled data.

Copied to clipboard

Thomas Müller, Guillermo Pérez-Torró, Marc Franco-Salvador

Low-Resource NLP

Challenge:	Recent studies have shown that few-shot text classification is a poor solution for training data-intensive tasks.
Approach:	They propose a method that embeds texts and labels into classifiers with proper pre-training.
Outcome:	The proposed approach reduces inference cost by increasing the number of labels and embeddings.

Query2doc: Query Expansion with Large Language Models (2023.emnlp-main)

Copied to clipboard

Liang Wang, Nan Yang, Furu Wei

PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning (2024.findings-emnlp)

Challenge:	Existing methods for sparse and dense retrieval have limited success on popular datasets.
Approach:	They propose a query expansion approach that generates pseudo-documents by few-shot prompting large language models and then expands the query with generated pseudo-docs.
Outcome:	The proposed method boosts the performance of BM25 on ad-hoc IR datasets by 3% to 15% without any model fine-tuning.

Copied to clipboard

Jiaru Zou, Mengyu Zhou, Tao Li, Shi Han, Dongmei Zhang

Structure Trumps Size: Rethinking Data Quality for LLM Reasoning (2025.findings-emnlp)

Challenge:	Recent advances in fine-tuning large language models have greatly enhanced their usage in domain-specific tasks.
Approach:	They propose a method which internalizes prompt knowledge during model fine-tuning to achieve efficient inference and save costs.
Outcome:	The proposed approach reduces input tokens by 90%, accelerates inference by 4.2 times, and reduces monetary inference costs by 88.3%.

Copied to clipboard

Hu Xu, Zeyan Li, Rui Wang, Jianfeng Xu

Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception (2025.coling-main)

Challenge:	Existing methods for fine-tuning Large Language Models rely on heuristic strategies and lack systematic, quantitative frameworks for evaluating data quality.
Approach:	They propose a multi-dimensional quantitative framework for reasoning data management . they rigorously evaluate and optimize datasets along six orthogonal dimensions .
Outcome:	The proposed framework rigorously evaluates and optimizes datasets along six orthogonal dimensions.

Copied to clipboard

Luyang Lin, Lingzhi Wang, Jinsong Guo, Kam-Fai Wong

Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection (2023.acl-long)

Challenge:	Detecting media bias is critical due to the spread of misinformation and disinformation on social media platforms.
Approach:	They investigate the presence and nature of bias within large language models and its consequential impact on media bias detection.
Outcome:	The proposed debiasing strategies include prompt engineering and model fine-tuning.

Copied to clipboard

Rheeya Uppaal, Junjie Hu, Yixuan Li

TAGS: A Test-Time Generalist–Specialist Framework with Retrieval-Augmented Reasoning and Verification (2026.findings-acl)

Challenge:	Out-of-distribution (OOD) detection is critical for reliable predictions over text . fine-tuning with pre-trained language models has been a de facto procedure .
Approach:	They propose to leverage pre-trained language models for OOD detection without fine-tuning on ID data.
Outcome:	The proposed approach outperforms the fine-tuned model under distributional shifts.

Copied to clipboard

Jianghao Wu, Feilong Tang, Yulong Li, Ming Hu, Haochen Xue, Shoaib Jameel, Zongyuan Ge, Yutong Xie, Imran Razzak

Low-Resource NLP

Challenge:	Existing efforts to improve medical question answering performance follow two directions.
Approach:	They propose a framework that combines a generalist with a domain-specific specialist without any model fine-tuning or parameter updates.
Outcome:	The proposed framework boosts GPT-4o accuracy by 13.8%, deepseek-R1 by 16.8%, and improves a vanilla 7B model from 14.1% to 23.9%.

Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery (2025.findings-acl)

Copied to clipboard

Yifan Sun, Danding Wang, Qiang Sheng, Juan Cao, Jintao Li

CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation (2024.findings-acl)

Challenge:	Existing concepts-based explainable approaches do not discover unseen concepts . a recent approach to solve this problem is concept-based explanations .
Approach:	They propose a framework that extracts comprehensible concepts automatically with no annotations . ECO-Concept uses an object-centric architecture to extract task-specific semantic concepts .
Outcome:	a new framework extracts comprehensible concepts with no concept annotations . the proposed framework outperforms existing methods in computability tests on diverse tasks .

Copied to clipboard

I-Hung Hsu, Zifeng Wang, Long Le, Lesly Miculicich, Nanyun Peng, Chen-Yu Lee, Tomas Pfister

Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification (2024.emnlp-main)

Challenge:	Existing methods to generate grounded responses are prone to errors due to the irrelevancy of input documents.
Approach:	They propose a framework that leverages the insight that a robust grounded response should be consistent with information derived solely from its cited sources.
Outcome:	Experiments on three open-domain question-answering datasets show that the proposed framework improves performance by 1.5% to 7% without any model fine-tuning.

Copied to clipboard

Ming Li, Jike Zhong, Chenxin Li, Liuzhuozheng Li, Nie Lin, Masashi Sugiyama

Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach (2025.findings-acl)

Challenge:	Recent advances in fine-tuning Vision-Language Models have seen the success of prompt tuning and adapter tuning.
Approach:	They propose a method to fine-tune CLIP without introducing any overhead of extra parameters.
Outcome:	The proposed method improves CLIP by 7.27% average harmonic mean accuracy.

Copied to clipboard

Yurong Wu, Fangwen Mu, Qiuhong Zhang, Jinjing Zhao, Xinrun Xu, Lingrui Mei, Yang Wu, Lin Shi, Junjie Wang, Zhiming Ding, Yiwei Wang

Are Dialects Better Prompters? A Case Study on Arabic Subjective Text Classification (2025.findings-acl)

Challenge:	Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates that can generate similar images.
Approach:	They propose a prompt-stealing benchmark consisting of 50 templates and 450 images organized into Easy and Hard difficulty levels.
Outcome:	The proposed method outperforms baseline methods with an average improvement of over 10%.

Copied to clipboard

Leila Moudjari, Farah Benamara

Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer (2023.emnlp-main)

Challenge:	specialized fine-tuned models with Arabic and Arabizi scripts achieve the best results . transfer learning demonstrated limited effectiveness, despite ability to adapt to other regionally specific varieties .
Approach:	They evaluate the performance of 12 open source LLMs for Arabic and Arabizi scripts . they highlight the impact of Arabic-centric LLM fine-tuning and prompt design on models .
Outcome:	The results show that specialized models with Arabic and Arabizi scripts achieve the best results .

Copied to clipboard

Ruize Gao, Zhirui Zhang, Yichao Du, Lemao Liu, Rui Wang

Retrieval-enriched zero-shot image classification in low-resource domains (2024.emnlp-main)

Challenge:	Nearest Neighbor Machine Translation (kNN-MT) is a powerful domain adaptation tool . the reasons for its success have not been thoroughly investigated .
Approach:	They propose to integrate pre-trained Neural Machine Translation models with token-level retrieval . they propose to implicitly execute gradient descent on the output projection layer of NMT .
Outcome:	The proposed approach outperforms model fine-tuning on in-domain tests while achieving better performance on out-of-domain sets.

Copied to clipboard

Nicola Dall’Asen, Yiming Wang, Enrico Fini, Elisa Ricci

Information Retrieval

Challenge:	Low-resource domains are those where data or annotations are scarce.
Approach:	They propose a retrieval-based method for low-resource domains that trains without training . they use web-crawled databases to retrieve relevant textual information from query images .
Outcome:	The proposed method outperforms existing training-based methods in low-resource domains . it retrieves relevant textual information from large web-crawled databases .

DIESEL: A Lightweight Inference-Time Safety Enhancement for Language Models (2025.findings-acl)

Copied to clipboard

Ben Ganon, Alon Zolfi, Omer Hofman, Inderjeet Singh, Hisashi Kojima, Yuval Elovici, Asaf Shabtai

FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering (2026.findings-acl)

Challenge:	Large language models generate outputs that are not aligned with human values, such as toxic content, malicious use cases, and vulnerabilities to adversarial jailbreak attacks.
Approach:	They propose a lightweight inference-guidance technique that can be seamlessly integrated into any autoregressive LLM to semantically filter undesirable content during generation.
Outcome:	The proposed technique can be integrated into any autoregressive LLM to semantically filter undesirable content during generation.

Copied to clipboard

Yixi Zhou, Fan Zhang, YU Chen, Haipeng Zhang, Preslav Nakov, Zhuohan Xie

Question Answering

Challenge:	Existing reranking frameworks optimize semantic relevance, leading to unstable rankings and opaque decisions on long documents.
Approach:	They propose a structured reranking framework that reframes financial evidence selection as constraint satisfaction under a finance-aware schema.
Outcome:	FINCARDS improves early-rank retrieval over lexical and LLM-based reranking baselines while reducing ranking variance.

LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks (2026.findings-acl)

Copied to clipboard

Jiayong Wan, Jiawei Chen, Zhaoxia Yin, Liu Shuyuan, Hang Su

What Do Vision–Language Models Encode for Personalized Image Aesthetics Assessment? (2026.findings-acl)

Challenge:	Existing defense methods are insufficient to address in-context reward hacking (ICRH), where LLMs iteratively optimize their behavior to maximize proxy objectives, resulting in harmful side effects.
Approach:	They propose a framework that reduces in-context reward hacking (ICRH) through repeated interactions with the environment.
Outcome:	The proposed framework reduces ICRH without model fine-tuning while maintaining task performance.

Copied to clipboard

Koki Ryu, Hitomi Yanaka

Defending LLMs against Jailbreak Attacks via Template-Based ICL with a Defensive Suffix (2026.findings-acl)

Challenge:	Personalized image aesthetics assessment (PIAA) is an important research problem with practical applications.
Approach:	They propose a vision-language model that encodes multi-level aesthetic attributes . they analyze visual representations of VLMs to examine their internal representations .
Outcome:	The proposed framework can be used to personalize images without fine-tuning . it can be implemented in a variety of image domains and architectures.

Copied to clipboard

Ruiyang Ni, Changlong Li, Shuaibiao Han, Zhiyu Yi, Perley Xu, Wenjie Ruan