OCR
-
From Retrieval to Recognition:How Vision--Language Models Become OCR Specialists
2026-09-18 09:32:37Yuanxiang Huangfu, Hanmeng Zhong, Linqing Chen, Jeffrey Tiong Jee HuiAbstract
Does a general vision--language model acquire specialized OCR ability by developing a new reading circuit or by reusing an existing mechanism? We address this question in the setting of full-sequence OCR, rather than local-answer retrieval. Using an evidence-grounded protocol with held-out causal interventions, we identify sparse and stable OCR-head sets in GLM-OCR, MinerU2.5, and PaddleOCR-VL-1.6. We then investigate the mechanistic origin of these OCR heads by comparing them with independently identified textual retrieval/copy heads in general VLMs. Across two general VLMs, visual OCR heads strongly overlap independently identified textual retrieval/copy heads, yielding untuned top-20 intersections of 73.3% and all-head Spearman correlations of 0.677-0.886. The overlap and causal interventions suggest that full-sequence OCR operates as dense sequential multimodal copy-and-paste, repeatedly retrieving visual evidence and routing it to the current output position. Finally, we examine how this shared circuit changes as a general VLM becomes an OCR specialist. Matched base-to-specialized comparisons show that OCR specialization largely preserves head identity, retaining 17-20 of the top 20 heads per task with all-head rank correlations of 0.874-0.942, while redistributing their functional and causal strengths.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21543
PDF
-
PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR
Abstract
Table extraction suffers from frequent structural errors and semantic hallucinations. We propose PrismAlign, a multi-VLM framework aligning diverse visual perspectives to resolve ambiguity. It integrates priors of table logic to assess output plausibility, decoupling structural alignment from cell content alignment. A Bayesian decision strategy maximizes alignment accuracy by exploiting the correlation between extraction errors and computable rule violations. Evaluated on open-source and custom VLMs, PrismAlign reduces hallucinations and achieves state-of-the-art performance on OmniDocBench 1.5, as well as on the table category of CC-OCR and PureDocBench.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21351
PDF
-
Developing an OCR model for Extracting Information from Invoices with Korean Language
2026-09-17 15:13:03Xiem HoangVan, Phu TranQuang, Minh DinhBao, Tien VuHuuAbstract
Invoices are commercial documents that contain various pieces of information, including the purchased items, time, and total money. Making the extraction of important information crucial. The stored information serves different purposes. Korean language is the native language of about 80 million people, playing an important role in not only South and North Korea but also in many other countries such as Vietnam, Philippine where a large number of Korean companies are located. In this context, to automatically extract proper information from the invoices with Korean language, we propose an efficient Optical Character Recognition (OCR) model in which a deep learning model is combined with some image preprocessing techniques. The proposed OCR model is assessed in a rich set of collected invoices showing that 87% F1-score can be achieved with negligible time processing.
Abstract (translated)
URL
https://arxiv.org/abs/2609.35796
PDF
-
A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition
2026-09-17 11:15:07Benjamin Kiessling (ALMAnaCH)Abstract
Despite impressive reported scores, large vision-language models have seen limited practical uptake in historical automatic text recognition because of their computational cost, dependence on large-scale pretraining, and hallucination. Historical ATR therefore continues to rely largely on compact CRNN line recognizers, which are visually grounded and trainable on modest data. Lightweight recurrence-free recognizers promise the accuracy of larger models with the practical advantages of CRNNs, yet have not been comprehensively evaluated on historical writing. We adapt PP-OCRv6, a recent compact text recognizer without strong language modeling, for historical line recognition and compare it with a conventional CRNN across generalized pretraining, domain-specific training, corpus-level fine-tuning, and manuscript-specific few-shot adaptation on multilingual Latin- and Arabic-script material. While PP-OCRv6 does not consistently outperform the baseline when trained from scratch, heterogeneous pretraining produces markedly better generalization. Comparisons with the Qwen3.5-based Medusa recognizer further show that fine-tuned PP-OCRv6 can outperform a large VLM tailored towards historical Latin-script HTR.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20064
PDF
-
AI Should Facilitate Democratic Deliberation at Scale
Abstract
AI systems can strengthen democracy by supporting deliberation at scale by addressing cognitive, social, platform-design, and market-driven frictions, while preserving human agency. Unlike proposals such as liquid democracy that restructure representation through vote delegation, in this position paper, we argue that AI-assisted deliberation offers a more promising path by lowering barriers to meaningful engagement without substituting machine judgment for human choice. Drawing on evidence from online deliberation platforms and experimental research, we identify four guiding principles: preserving agency and autonomy, encouraging mutual respect, promoting equality and inclusiveness, and augmenting rather than substituting active citizenship. We also address critical challenges, including alignment, sycophancy, training bias, and over-reliance on AI systems. We call on the machine learning community to develop deliberation-focused AI systems evaluated not on engagement metrics but on their capacity to facilitate informed, representative, and friction-robust discourse.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20059
PDF
-
TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives
2026-09-17 08:44:36Donghan Bian (ENC, LRE), Marie Puren (LRE, ENC), Florian Cafiero (LRE, ENC)Abstract
Historical archives pose a difficult retrieval problem for retrievalaugmented generation systems: documents are OCR-degraded, heterogeneous across genres and sources, and require strong source traceability for scholarly and institutional use. We introduce TRACE, a training-free agentic retrieval framework designed for accountable source discovery over historical corpora. The system was developed in the context of DECIDON, an interdisciplinary project on the circulation of political discourse between parliamentary debates and the press during the French Third Republic, involving digitised historical collections and institutional use cases. The prototype is currently deployed internally within the project and accessible to 24 researchers across six partner institutions. We evaluate TRACE on HistoriQA-ThirdRepublic, a benchmark of 1,752 French historical questions over parliamentary debates and newspapers from 1887, with documents derived from Biblioth{è}que nationale de France digitised collections. TRACE achieves R@10 = 0.856 and MRR = 0.653, outperforming sparse, dense, graph-based, and agentic RAG baselines, with the largest gains on multi-hop and cross-corpus questions. At approximately $0.02 per question under the default hosted inference configuration, TRACE also remains economically feasible for heritage institutions, laboratories or companies that cannot rely on costly local GPU infrastructure. These results suggest that, for large digital libraries and archives, retrieval accountability and corpus-aware agent design can provide a practical alternative to heavier training-based or graph-construction approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2609.19897
PDF
-
Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention
2026-09-17 04:59:56Jongbin Won, Sung Geun An, Jay-yoon LeeAbstract
Just as Socrates recognized the limits of his own knowledge, Retrieval-Augmented Language Models (RALMs) should learn to abstain when the retrieved evidence cannot support a reliable response. Existing approaches largely rely on monolithic LLMs to handle heterogeneous retrieval failures in a single step, resulting in limited abstention performance and high computational costs. We instead decompose retrieval failures into two distinct states: (i) the unanswerable state, where the required evidence is absent, and (ii) the distracted state, where relevant evidence is mixed with conflicting, negated, or adversarial information. Based on this decomposition, we introduce a lightweight module (Sieve) that screens retrieved document sets for distracting evidence before invoking a costly LLM (Sage) for grounded generation and abstention. Evaluated across both general and high-stakes expert domains, our Sieve and Sage framework preemptively detects distracting noise, improving system accuracy by up to 69.4 percentage points and Macro-F1 by 55.2 percentage points compared to one-stage baselines. Furthermore, it achieves up to a 1.99x speedup, establishing a highly efficient and reliable abstention pipeline for RALM with abstention.
Abstract (translated)
URL
https://arxiv.org/abs/2609.35794
PDF
-
LinePilot Digitizer: Line-Plot Recovery with Manual and Automatic Calibration
2026-09-16 19:56:11Fengbo Ma, Rayan Akhtar, Aakash H. Joshi, Xiaoting Li, Haijian Sun, Zhen Xiang, Xianyan Chen, Yiping ZhaoAbstract
Recovering numerical series from line plots requires accurate axis calibration and reliable curve extraction. We present LinePilot Digitizer (LinePilot), which combines continuous color-based curve recovery with three calibration modes: LinePilot (standard), LinePilot (enhanced), and LinePilot (OCR). We also introduce DigitizerBench, the first dedicated benchmark for systematically evaluating digitizer performance, using an orthogonal design spanning signal, rendering, and plot-structure factors with complementary automatic and human-guided evaluations. We evaluate performance using failure-penalized capped normalized root-mean-square error (FPC-NRMSE), which assigns unit loss to missing, unusable, or catastrophically inaccurate outputs. On DigitizerBench-Full, LinePilot (OCR) achieves the lowest mean FPC-NRMSE (0.672) and highest trusted usability (38.2%) among the tested automatic pipelines. On DigitizerBench-Lite, LinePilot (enhanced) achieves the lowest mean FPC-NRMSE (0.081), 100% output success, and highest trusted usability (93.3%). The orthogonal benchmark design further enables factor analysis to identify the factors that most significantly affect digitizer performance. Together, the three calibration modes provide a practical trade-off between automation, user control, and accuracy within a shared curve-recovery workflow.
Abstract (translated)
URL
https://arxiv.org/abs/2609.19377
PDF
-
Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection
2026-09-16 16:00:36Girish A. Koushik, Diptesh Kanojia, Helen TreharneAbstract
When a large vision-language model misclassifies a harmful meme, the failure may reflect missing internal evidence or an inability to route represented evidence to its output. We distinguish these cases in Gemma-3 and Qwen3.5 using sparse autoencoders, role-conditioned probes, causal interventions, and recovery experiments across six harmful content benchmarks, with additional Spanish and Hindi-English code-mixed evaluations. Sparse readouts outperform native prediction on all six primary binary tasks: Qwen averages $0.740$ versus $0.432$ native macro-F1, while residual reconstruction reaches $0.486$, whereas Gemma improves from $0.532$ to $0.714$. These differences reflect supervised accessibility rather than a pre-existing, native decision rule, and the most influential token role depends on the task. Under the evaluated score scales, Qwen silent-feature ablation is $24-63$ times more probe-sensitive, whereas routed-feature patching on literal yes/no tasks is $16-140$ times more output-sensitive. Calibration-only routing recovers $93.3$% of the mean gap, and probe-distilled LoRA improves native predictions, although shared multi-task adaptation causes negative transfer. A case study of Gemma-3-12B on Facebook Hateful Memes finds a distributed rank-32 image-prompt interaction, reaching $0.756$ versus $0.685$ native macro-F1. Robustness controls show that the signal extends beyond English, is not explained solely by accompanying OCR, and depends on paired visual evidence. Thus, routing, rather than representation alone, is a recurring bottleneck in harmful meme classification.
Abstract (translated)
URL
https://arxiv.org/abs/2609.18860
PDF
-
Using OCR Heads to Verbalize Image Semantics
2026-09-16 15:30:17Sheridan Feucht, Benno Krojer, Sarah Wang, Henry Abrahamsen, Byron C. Wallace, David BauAbstract
How do VLMs map from pixels to semantics? To understand this general question, we focus on a narrow one: studying how VLMs perform optical character recognition (OCR). Across four models, we identify attention heads causally necessary for OCR, and discover that these are in fact general-purpose heads that output interpretable semantic features across all image tokens. For example, pointing these heads at an image token containing the word "bike" causes Qwen3-VL-8B to output "bike," but pointing them at a bird wing causes the model to output the token "feathers." We collapse these heads' attention weights into a single verbalization lens transformation that reveals interpretable semantic features in hidden states across all layers. When combined with projection to vocabulary space, we can obtain interpretable labels starting from layer 0, showing that image representations are in fact aligned with language in early layers. We find that we can also use the inverse of this transformation to edit non-word concepts, e.g., replacing a tractor with a revolver in a naturalistic image, providing causal evidence that this subspace is useful for more than just OCR. Our results are an example of how the study of specific mechanisms can shed light on broader interpretability problems.
Abstract (translated)
URL
https://arxiv.org/abs/2609.18823
PDF
-
Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification
2026-09-16 13:50:55Seungmin Seo, Oleg Aulov, P. Jonathon Phillips, Kevin Mangold, Jonathan EskinAbstract
Speaker de-identification (SDID) aims to preserve privacy by concealing speaker identity while maintaining speech utility. However, current evaluations often reduce privacy to a single dimension - biometric verification performance - typically measured by Equal Error Rate (EER). This narrow focus ignores critical leakage channels, such as soft biometric inference, embedding-level re-identification, and structural template similarity, which threaten the unlinkability and irreversibility of biometric references. We propose a holistic evaluation framework across five complementary metrics: (i) EER, (ii) soft biometric leakage score , (iii) cumulative match characteristic re-identification analysis, (iv) canonical correlation analysis and Procrustes embedding alignment, and (v) intelligibility via word error rate and semantic similarity. Evaluating five SDID systems from the IARPA ARTS program, we demonstrate that these metrics capture independent dimensions of information leakage. Our results indicate that reliance on a single metric can misrepresent the privacy properties of an SDID system.
Abstract (translated)
URL
https://arxiv.org/abs/2609.18673
PDF
-
Tables Decoded: DELTA for Structure, TARQA for Understanding
2026-09-15 16:59:42Jahanvi Rajput, Dhruv Kudale, Saikiran Kasturi, Utkarsh Verma, Ganesh RamakrishnanAbstract
Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approaches predominantly rely on vision- language models (VLMs) operating on table images, we propose a more scalable and effective alternative based on structured textual representations. These representations are easier to process, align more naturally with LLMs, and eliminate the need for language-specific visual encoders, making them particularly suitable for multilingual documents. We present DELTA, which separates physical structure recognition, logical structure recognition, and OCR to extract both layout and content accurately. DELTA outputs tables in Optimised Table Structure Language (OTSL), a compact and unified format that encodes cell arrangements and textual content. On table structure recognition (TSR), DELTA achieves TEDS- Structure scores comparable with state-of-the-art methods across FinTabNet, PubTabNet, and PubTables-1M. We further establish its robustness on non-English tables through our curated Hindi benchmark, TORQUE. Building on this, we introduce TARQA, an LLM fine-tuned on OTSL sequences. Our approach yields gains of 9.3 p.p. on WTQ (TabQA) and 9.2 p.p. on FinTabNetQA (TabVQA), respectively. On TORQUE, our method ranks second among all VLMs and DELTA + LLM variants. We release our code, models, and benchmark at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.17458
PDF
-
Reduplicative constructions in Mandarin: Socio-emotional profiling through distributional semantics
2026-09-15 08:51:41Chaoyi Wu, Yu-Hsiang Tseng, R. Harald BaayenAbstract
Mandarin Chinese has two productive reduplicative constructions that repeat either two-character base words or their constituents (e.g., `in good health', `discuss a bit'). Their varied meanings have been described as realizing plurality, valence coloring, sound symbolism and pragmatic functions. The aim of this study is twofold. A first goal is to clarify whether it is possible to come to a more precise understanding of the variegated semantics of Mandarin reduplication by using word embeddings from distributional semantics. A second goal is to explore how useful embeddings are for understanding the details of a semantically complex word-formation process. We show that the embedding space recovers the semantic and grammatical properties of reduplications previously identified in the literature, validating Tencent embeddings for morphological investigation. Semantic profiling revealed that reduplicative constructions are often strongly represented on multiple dimensions. The two patterns exhibit clear semantic and pragmatic differentiation in distributional space. Procrustes analysis clarified that the overall organization of the base-word space is largely preserved in the reduplication space, with local mismatches highlighting regions of discourse-pragmatic reorganization. Taken together, these results show that high-dimensional word embeddings can recover established linguistic generalizations, and capture the semantic versatility of Mandarin reduplication and constructional transparency.
Abstract (translated)
URL
https://arxiv.org/abs/2609.16860
PDF
-
From Manual Construction to AI-Driven Scenario Emergence: Rethinking Catastrophe Risk Modeling
Abstract
Traditional catastrophe (CAT) risk models rely on costly manual construction to generate extreme weather scenarios, an approach largely unchanged since the 1990s. As climate extremes intensify, this creates mounting challenges to the entire risk transfer chain. This study proposes the TAISE framework, which repurposes AI weather forecasting models to produce coherent extreme weather sequences at a fraction of traditional costs. Through self-iterative generation, the framework produces continuous global atmospheric fields from which extreme events emerge. A proof-of-concept experiment demonstrates an order-of-magnitude reduction in computational cost compared with conventional methods, while capturing temporal continuity and cross-regional correlations absent in snapshot-based approaches. These findings suggest a pathway toward democratising catastrophe risk quantification and enabling dynamic, comprehensive portfolio assessment for insurers, reinsurers, ILS fund managers and public-sector risk managers.
Abstract (translated)
URL
https://arxiv.org/abs/2609.16493
PDF
-
Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks
2026-09-14 16:33:10Sebastiano Nordio, Michele LottoAbstract
The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posing a escalating risk as these models can bypass proprietary API guardrails when deployed locally. However, SLMs deployed as autonomous agents often struggle with long-horizon, exploratory tasks like cybersecurity Capture The Flag (CTF) challenges due to context bloat and cognitive degradation from accumulated tool-call outputs. To understand and mitigate this cybersecurity threat, we introduce context segmentation, a two-level agentic framework that divides complex exploitation tasks into manageable, contextually isolated sub-problems. Evaluating on the picoCTF dataset using memory-constrained gemma-4 models, we demonstrate that for the E4B model, our strategy acts as an intelligent search, achieving competitive rewards with superior token efficiency compared to brute-force retries, and successfully solving 18.52% of tasks that standard agentic execution fails to complete. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.12839
PDF
-
New Conditions for Philosophers to Catch the Wave of Citizen Deliberation in the Age of Artificial Intelligence in advance
2026-09-14 15:11:02Bernard Reber (CEVIPOF)Abstract
Powerful technologies labeled ``AI''-without sufficient epistemic caution-are already reshaping political and private life, bringing both new dangers and new opportunities for citizen participation. These range from electoral and legislative engagement to the most ambitious form: political co-creation through citizens' assemblies. Large Language Models (LLMs) could support such processes through moderation, translation, facilitation, summarization, and writing assistance. But this potential remains largely unrealized. The Democratic Commons project takes a fundamentally interdisciplinary approach-from philosophy to computer science-to evaluate LLMs against five proposed democratic principles. At its core, the project is driven by the question of political bias: under what conditions can LLMs be used democratically within forms of citizen participation that are them- selves still largely experimental? Addressing these socio-technical questions requires grounding in political theory and, more broadly, in philosophy-disciplines that provide the normative frameworks without which the democratic evaluation of AI systems cannot be mean- ingfully conducted.
Abstract (translated)
URL
https://arxiv.org/abs/2609.15707
PDF
-
Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction
2026-09-14 15:10:33Kushal Patel, Pushkal Shrivastava, Mackenzie Lees, Qirui Lu, Bhargobjyoti Saikia, Liying Li, Junlin JiangAbstract
Vision-language models (VLMs) are increasingly used to extract structured fields from business documents, yet most evaluations report accuracy on clean benchmarks and offer little guidance to practitioners choosing an approach for a given task complexity. We address this gap with a measurement-grounded study and an open-source release. Across eleven systems (three commercial, two reasoning, five open-source VLMs in pretrained and fine-tuned form, and a non-LLM OCR->regex floor) scored on a 750-document held-out pool of synthetic checks, fine-tuning on 3K samples lifts the best open-source VLMs above F1 0.98-above every zero-shot commercial system on this task-while GPT-5 leads the commercial pool on F1 and Claude Sonnet 4.5 collapses on Date. To turn these measurements into actionable choices, we introduce a practitioner-oriented selection framework that maps a task profile (quality, latency, governance, volume) to a recommended approach via filtering and total-cost minimization, illustrated on a hypothetical mid-volume document-extraction scenario.
Abstract (translated)
URL
https://arxiv.org/abs/2609.15706
PDF
-
A Conservative OCR-Enabled Workflow for R214 Sodium Screening of South African Packaged Foods
2026-09-14 11:55:32Mayimunah Nagayi, Alice Scaria Khan, Tamryn Frank, Rina Swart, Clement NyirendaAbstract
Using food package images to monitor sodium and salt content against South Africa's R214 sodium limits is challenging when screening decisions require product identity, nutrition facts panel evidence, reporting basis, and category-specific thresholds. This study presents a conservative image-based workflow that combines region detection, optical character recognition (OCR), product identity and sodium evidence extraction, R214 category assignment, deterministic threshold comparison, and independent vision language model comparison. The evaluation used 442 packaged food products and 3 929 full package images from a real-world South African food packaging dataset. A YOLO26s small detector generated 4 195 region crops, and strict post-processing produced one sodium evidence row per product. The integrated workflow produced 290 OUTSIDE R214 SCOPE, 139 REVIEW, seven SCREEN-PASS, and six SCREEN-FAIL outcomes. The independent Qwen2.5-VL 7B vision language model workflow produced 387 OUTSIDE R214 SCOPE, 31 REVIEW, twenty SCREEN-PASS, and four SCREEN-FAIL outcomes. The workflows agreed on exact R214 category assignment for 415 of 442 products (93.9%) and on whether the assigned category was within R214 scope for 416 of 442 products (94.1%). Final screening outcome agreement was 307 out of 442 products, or 69.5%. Manual verification on 60 products showed lower strict outcome agreement than regulated status agreement, while all manual INSUFFICIENT DATA cases were kept out of SCREEN-PASS and SCREEN-FAIL by both automated workflows. The findings show that conservative image-based screening can organise package evidence, identify clear cases, and assign uncertain cases to REVIEW rather than forcing SCREEN-PASS or SCREEN-FAIL decisions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.15427
PDF
-
Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
2026-09-14 08:28:14Bastiaan Bruinsma, Annika Fred\'en, Paul R\"ottger, Moa Johansson, Asad SayeedAbstract
Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before elections. With growing evidence that they influence users' opinions, it is increasingly important to understand the views and positions of these tools. To better understand these views, we examine the stances supplied by six LLMs on a variety of Swedish-language writing tasks ahead of the 2026 Swedish parliamentary election. We cross 107 policy propositions with 77 writing templates and neutral, positive, and negative prompt framings, producing 24,717 prompts per model and 148,302 responses. To study these, we look at the models' default stance tendencies, compare how they respond to similar issues, and compare their responses with those of each of Sweden's eight parliamentary parties on the same issue. We find that Claude, DeepSeek, Gemini, and Mistral have similar profiles; ChatGPT more often supplies neutral or ambivalent text; and Grok differs most on topics such as migration, crime, and gender. When comparing the political parties, we find that the Social Democrats are closest to all six models. Still, after correcting for multiple comparisons, none of the within-model differences in party distances remains significant. Overall, we find that no model has a clear preference, nor a clear preference for a party, but that this depends on the specific issue or task the user asks about.
Abstract (translated)
URL
https://arxiv.org/abs/2609.15207
PDF
-
A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement
2026-09-12 23:00:19Carmel Kronfeld, Sharva Gogawale, Tetsuro Kobayashi, Irad Ben-GalAbstract
The rapid diffusion of hate speech and misinformation on social networks challenges democratic societies, since direct suppression efforts may deepen polarization, fuel public distrusts, and strengthen extremist narratives. LLM-driven counter-narratives (CNs) offer a promising way to reduce those risks, yet their effectiveness depends on rhetorical and stylistic choices that remain poorly understood. We present a multi-stage agent-based framework for generating, refining, and evaluating CNs, applied to pro-Russian hate and misinformation narratives on the war with Ukraine and adaptable to other domains. A pilot experiment with human evaluators identifies effective technique style pairings, such as repetition with emotional framing enhancing persuasiveness. Building on these insights, we introduce a multi-agent refinement process that iteratively improves CNs for persuasiveness, emotional engagement, and shareability. After human validation confirmed improvement, an automated safety analysis shows that our refined CNs match or improve on expert-written counterspeech. A simulated experiment then shows that they reduce the perceived strength of pro-Russian narratives and consistently outperform a vanilla LLM baseline, highlighting a pathway toward scalable, narrative-specific interventions against hate speech and misinformation. Code and data accompanying this work are publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.14178
PDF
