pith. machine review for the scientific record. sign in

arxiv: 2605.02695 · v1 · submitted 2026-05-04 · 💻 cs.CL · cs.AI

Recognition: 1 theorem link

mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection

Dominik Macko , Alok Debnath , Jakub Simko
Authors on Pith no claims yet

Pith reviewed 2026-05-08 18:53 UTC · model grok-4.3

classification 💻 cs.CL cs.AI
keywords multilingual polarization detectionLLM finetuningQLoRAdata augmentationSemEval-2026homoglyphssequence classificationparameter-efficient training
0
0 comments X

The pith

Finetuning mid-size LLMs with QLoRA on augmented multilingual data enables polarization detection across 22 languages and three subtasks.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper describes a method to tackle SemEval-2026 Task 9 on multilingual polarization detection by finetuning mid-size large language models. It uses the QLoRA technique for parameter-efficient training and augments the data from 22 languages with anonymized, lower-cased, upper-cased, and homoglyphied versions to enhance robustness. A sympathetic reader would care if this works because online polarization can lead to hate speech and social division, making early detection valuable for creating safer digital spaces. The system addresses the subtasks of identifying polarization, its type, and its manifestation.

Core claim

The authors cope with the multilingual polarization detection task by finetuning mid-size LLMs for sequence classification using QLoRA parameter-efficient finetuning. They augment the training sets covering 22 languages with anonymized, lower-cased, upper-cased, and homoglyphied counterparts to make the detection more robust across the axes of detection, type, and manifestation.

What carries the argument

QLoRA-based parameter-efficient finetuning applied to augmented multilingual training data for sequence classification

If this is right

  • The approach covers detection of polarization along with its type and manifestation in a single framework.
  • Data augmentation with case changes and homoglyphs improves handling of text variations in multiple languages.
  • Parameter-efficient finetuning allows mid-size models to be adapted without excessive computational resources.
  • Robustness is achieved for multicultural and multievent polarization in online discourse.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Without reported metrics, the claim of improved robustness cannot be verified from the paper alone.
  • This method could potentially apply to other multilingual text classification problems involving noisy inputs.
  • Testing the same augmentations on full fine-tuning or other efficient methods would clarify their specific contribution.

Load-bearing premise

The load-bearing premise is that the QLoRA finetuning on this specific augmented data will produce robust detection of polarization without the need for reported performance metrics or baseline comparisons.

What would settle it

Observing that the system fails to outperform standard baselines or achieves low accuracy on the official SemEval test sets for polarization detection, type, or manifestation would disprove the robustness claim.

read the original abstract

SemEval-2026 Task 9 is focused on multilingual polarization detection. Specifically, it covers the identification of multilingual, multicultural and multievent polarization along three axes (in subtasks), namely detection, type, and manifestation. Online polarization presents a concern, because it is often followed by hate speech, offensive discourse, and social fragmentation. Therefore, its detection before it escalates is crucial for a safer and more inclusive online space. We have coped with this SemEval task by finetuning mid-size LLMs for the sequence-classification task using the QLoRA parameter-efficient finetuning technique. The training data augmented the multilingual (22 languages) training sets by anonymized, lower-cased, upper-cased, and homoglyphied counterparts, making the detection more robust.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 3 minor

Summary. The manuscript describes a system submitted to SemEval-2026 Task 9 on multilingual polarization detection across three subtasks (detection, type, and manifestation). The approach consists of fine-tuning mid-size LLMs for sequence classification via QLoRA on a 22-language training set that has been augmented with anonymized, lower-cased, upper-cased, and homoglyphied variants, with the explicit goal of increasing robustness to multilingual, multicultural, and multievent polarization.

Significance. If the data-augmentation and QLoRA pipeline were shown to deliver measurable robustness gains, the work would offer a practical, parameter-efficient recipe for multilingual polarization detection that could be directly useful for online safety applications. At present, however, the absence of any quantitative results prevents assessment of whether the claimed robustness improvement is real or merely asserted.

major comments (2)
  1. The central claim that the described augmentation 'making the detection more robust' (abstract) is unsupported by evidence. The manuscript contains no results section, no performance tables, no F1/accuracy numbers on held-out or test data for any of the three subtasks, no baseline comparisons (e.g., non-augmented QLoRA or standard fine-tuning), and no ablation isolating the contribution of anonymization, casing, or homoglyph augmentation.
  2. Without reported metrics or error analysis it is impossible to verify that the system actually improves robustness across languages or polarization manifestations; the robustness assertion therefore remains an untested hypothesis rather than a demonstrated outcome.
minor comments (3)
  1. The specific LLMs (model names, parameter counts) and the exact QLoRA configuration (rank, alpha, target modules) are not stated.
  2. Implementation details of the data augmentation pipeline (e.g., how many augmented copies per original instance, how homoglyphs were generated, whether augmentation was applied only to training or also to validation) are missing.
  3. The title references 'mdok-style' but the term is never defined or referenced in the body of the paper.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments on our system description paper for SemEval-2026 Task 9. We address each major comment below and indicate the revisions we will incorporate.

read point-by-point responses

  1. Referee: The central claim that the described augmentation 'making the detection more robust' (abstract) is unsupported by evidence. The manuscript contains no results section, no performance tables, no F1/accuracy numbers on held-out or test data for any of the three subtasks, no baseline comparisons (e.g., non-augmented QLoRA or standard fine-tuning), and no ablation isolating the contribution of anonymization, casing, or homoglyph augmentation.

    Authors: We agree that the manuscript as currently written does not contain quantitative results, tables, baselines, or ablations, leaving the robustness claim unsupported. The paper is a system description submitted to the shared task, with emphasis on the methodology. In the revised version we will add a dedicated results section reporting F1 and accuracy on the development set for all three subtasks, direct comparisons against non-augmented QLoRA baselines, and an ablation study that isolates the effect of each augmentation component (anonymization, case variation, and homoglyph substitution). revision: yes

  2. Referee: Without reported metrics or error analysis it is impossible to verify that the system actually improves robustness across languages or polarization manifestations; the robustness assertion therefore remains an untested hypothesis rather than a demonstrated outcome.

    Authors: We acknowledge the validity of this point. The absence of metrics and error analysis prevents empirical verification of cross-lingual and cross-manifestation robustness. We will revise the manuscript to include development-set performance numbers broken down by language and by polarization manifestation, together with a concise error analysis highlighting cases where the augmented training data yields measurable gains over the non-augmented baseline. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical system description without derivations or self-referential claims

full rationale

The paper describes an applied system for a SemEval shared task: finetuning mid-size LLMs via QLoRA on augmented multilingual training data (anonymized, cased, and homoglyph variants). No equations, first-principles derivations, fitted parameters renamed as predictions, or load-bearing self-citations appear in the provided text. The robustness claim is an un-evidenced assertion rather than a reduction of any output to its own inputs by construction. This is a standard empirical pipeline report with no circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper relies on standard assumptions of machine learning (that fine-tuning on augmented data improves generalization) without introducing new free parameters, axioms, or invented entities. No mathematical derivations or novel postulates are present.

pith-pipeline@v0.9.0 · 5442 in / 1092 out tokens · 44373 ms · 2026-05-08T18:53:27.336865+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

300 extracted references · 147 canonical work pages

  1. [1]

    Proceedings of the 20th International Workshop on Semantic Evaluation (SemEval-2026) , year =

    Naseem, Usman and Geislinger, Robert and Ren, Juan and Kohail, Sarah and Garrido Veliz, Rudy and Sam Sahil, P and Zhang, Yiran and Stranisci, Marco Antonio and Abdulmumin, Idris and Alacam,. Proceedings of the 20th International Workshop on Semantic Evaluation (SemEval-2026) , year =

    2026

  2. [2]

    2026 , eprint=

    POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization , author=. 2026 , eprint=

    2026

  3. [3]

    2025 , eprint=

    Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors , author=. 2025 , eprint=

    2025

  4. [4]

    Dominik Macko , year=. mdok of. 2506.01702 , archivePrefix=

    work page arXiv

  5. [5]

    Voight-Kampff

    Janek Bevendorff and Yuxia Wang and Jussi Karlgren and Matti Wiegmann and Maik Fr. Overview of the "Voight-Kampff" Generative. Working Notes of

  6. [6]

    Working Notes of

    Dominik Macko , title =. Working Notes of

  7. [7]

    2025 , eprint=

    Authorship Attribution in Multilingual Machine-Generated Texts , author=. 2025 , eprint=

    2025

  8. [8]

    Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke , booktitle =

  9. [9]

    2025 , eprint=

    Gemma 3 Technical Report , author=. 2025 , eprint=

    2025

  10. [10]

    2025 , eprint=

    Qwen3 Technical Report , author=. 2025 , eprint=

    2025

  11. [11]

    Journal of personality and social psychology , volume=

    Evidence for universality and cultural variation of differential emotion response patterning , author=. Journal of personality and social psychology , volume=. 1994 , publisher=

    1994

  12. [12]

    Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages=

    Unsupervised Cross-lingual Representation Learning at Scale , author=. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages=

  13. [13]

    Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics , pages=

    Crowdsourcing and validating event-focused emotion corpora for German and English , author=. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics , pages=

  14. [14]

    Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  15. [15]

    Research on LLM s-Empowered Conversational AI for Sustainable Behaviour Change

    Chen, Ben. Research on LLM s-Empowered Conversational AI for Sustainable Behaviour Change. Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  16. [16]

    Deep Reinforcement Learning of LLM s​ using RLHF

    Levandovsky, Enoch. Deep Reinforcement Learning of LLM s​ using RLHF. Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  17. [17]

    Conversational Collaborative Robots

    Kranti, Chalamalasetti. Conversational Collaborative Robots. Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  18. [18]

    Dialogue System using Large Language Model-based Dynamic Slot Generation

    Hashimoto, Ekai. Dialogue System using Large Language Model-based Dynamic Slot Generation. Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  19. [19]

    Towards Adaptive Human-Agent Collaboration in Real-Time Environments

    Nakae, Kaito. Towards Adaptive Human-Agent Collaboration in Real-Time Environments. Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  20. [20]

    Towards Human-Like Dialogue Systems: Integrating Multimodal Emotion Recognition and Non-Verbal Cue Generation

    Jiang, Jingjing. Towards Human-Like Dialogue Systems: Integrating Multimodal Emotion Recognition and Non-Verbal Cue Generation. Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  21. [21]

    Controlling Dialogue Systems with Graph-Based Structures

    Hilgendorf, Laetitia Mina. Controlling Dialogue Systems with Graph-Based Structures. Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  22. [22]

    Multimodal Agentic Dialogue Systems for Situated Human-Robot Interaction

    Sucal, Virgile. Multimodal Agentic Dialogue Systems for Situated Human-Robot Interaction. Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  23. [23]

    Knowledge Graphs and Representational Models for Dialogue Systems

    Walker, Nicholas Thomas. Knowledge Graphs and Representational Models for Dialogue Systems. Proceedings of the 21st Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems. 2025

    2025

  24. [24]

    Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.0

    work page doi:10.18653/v1/2025.xllm-1.0 2025

  25. [25]

    Fine-Tuning Large Language Models for Relation Extraction within a Retrieval-Augmented Generation Framework

    Efeoglu, Sefika and Paschke, Adrian. Fine-Tuning Large Language Models for Relation Extraction within a Retrieval-Augmented Generation Framework. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.1

    work page doi:10.18653/v1/2025.xllm-1.1 2025

  26. [26]

    Benchmarking Table Extraction: Multimodal LLM s vs Traditional OCR

    Nunes, Guilherme and Rolla, Vitor and Pereira, Duarte and Alves, Vasco and Carreiro, Andre and Baptista, M \'a rcia. Benchmarking Table Extraction: Multimodal LLM s vs Traditional OCR. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.2

    work page doi:10.18653/v1/2025.xllm-1.2 2025

  27. [27]

    Injecting Structured Knowledge into LLM s via Graph Neural Networks

    Li, Zichao and Ke, Zong and Zhao, Puning. Injecting Structured Knowledge into LLM s via Graph Neural Networks. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.3

    work page doi:10.18653/v1/2025.xllm-1.3 2025

  28. [28]

    Regular-pattern-sensitive CRF s for Distant Label Interactions

    Papay, Sean and Klinger, Roman and Pad \'o , Sebastian. Regular-pattern-sensitive CRF s for Distant Label Interactions. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.4

    work page doi:10.18653/v1/2025.xllm-1.4 2025

  29. [29]

    From Syntax to Semantics: Evaluating the Impact of Linguistic Structures on LLM -Based Information Extraction

    Swarup, Anushka and Bhandarkar, Avanti and Wilson, Ronald and Pan, Tianyu and Woodard, Damon. From Syntax to Semantics: Evaluating the Impact of Linguistic Structures on LLM -Based Information Extraction. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.5

    work page doi:10.18653/v1/2025.xllm-1.5 2025

  30. [30]

    Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models

    Willemsen, Bram and Skantze, Gabriel. Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.6

    work page doi:10.18653/v1/2025.xllm-1.6 2025

  31. [31]

    Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis

    Li, Daoyang and Zhao, Haiyan and Zeng, Qingcheng and Du, Mengnan. Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.7

    work page doi:10.18653/v1/2025.xllm-1.7 2025

  32. [32]

    Self-Contrastive Loop of Thought Method for Text-to- SQL Based on Large Language Model

    Kang, Fengrui and Tan, Mingxi and Huang, Xianying and Yang, Shiju. Self-Contrastive Loop of Thought Method for Text-to- SQL Based on Large Language Model. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.8

    work page doi:10.18653/v1/2025.xllm-1.8 2025

  33. [33]

    Combining Automated and Manual Data for Effective Downstream Fine-Tuning of Transformers for Low-Resource Language Applications

    Isaeva, Ulyana and Astafurov, Danil and Martynov, Nikita. Combining Automated and Manual Data for Effective Downstream Fine-Tuning of Transformers for Low-Resource Language Applications. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.9

    work page doi:10.18653/v1/2025.xllm-1.9 2025

  34. [34]

    Seamlessly Integrating Tree-Based Positional Embeddings into Transformer Models for Source Code Representation

    Bartkowiak, Patryk and Grali \'n ski, Filip. Seamlessly Integrating Tree-Based Positional Embeddings into Transformer Models for Source Code Representation. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.10

    work page doi:10.18653/v1/2025.xllm-1.10 2025

  35. [35]

    Enhancing AMR Parsing with Group Relative Policy Optimization

    Barta, Botond and Hamerlik, Endre and Nyist, Mil \'a n and Ito, Masato and Acs, Judit. Enhancing AMR Parsing with Group Relative Policy Optimization. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.11

    work page doi:10.18653/v1/2025.xllm-1.11 2025

  36. [36]

    Structure Modeling Approach for UD Parsing of Historical M odern J apanese

    Ozaki, Hiroaki and Omura, Mai and Komiya, Kanako and Asahara, Masayuki and Ogiso, Toshinobu. Structure Modeling Approach for UD Parsing of Historical M odern J apanese. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.12

    work page doi:10.18653/v1/2025.xllm-1.12 2025

  37. [37]

    BARTABSA ++: Revisiting BARTABSA with Decoder LLM s

    Pfister, Jan and V. BARTABSA ++: Revisiting BARTABSA with Decoder LLM s. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.13

    work page doi:10.18653/v1/2025.xllm-1.13 2025

  38. [38]

    Typed- RAG : Type-Aware Decomposition of Non-Factoid Questions for Retrieval-Augmented Generation

    Lee, DongGeon and Park, Ahjeong and Lee, Hyeri and Nam, Hyeonseo and Maeng, Yunho. Typed- RAG : Type-Aware Decomposition of Non-Factoid Questions for Retrieval-Augmented Generation. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.14

    work page doi:10.18653/v1/2025.xllm-1.14 2025

  39. [39]

    Do we still need Human Annotators? Prompting Large Language Models for Aspect Sentiment Quad Prediction

    Hellwig, Nils Constantin and Fehle, Jakob and Kruschwitz, Udo and Wolff, Christian. Do we still need Human Annotators? Prompting Large Language Models for Aspect Sentiment Quad Prediction. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.15

    work page doi:10.18653/v1/2025.xllm-1.15 2025

  40. [40]

    Can LLM s Interpret and Leverage Structured Linguistic Representations? A Case Study with AMR s

    Raut, Ankush and Zhu, Xiaofeng and Pacheco, Maria Leonor. Can LLM s Interpret and Leverage Structured Linguistic Representations? A Case Study with AMR s. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.16

    work page Pith review doi:10.18653/v1/2025.xllm-1.16 2025

  41. [41]

    LLM Dependency Parsing with In-Context Rules

    Ginn, Michael and Palmer, Alexis. LLM Dependency Parsing with In-Context Rules. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.17

    work page doi:10.18653/v1/2025.xllm-1.17 2025

  42. [42]

    Cognitive Mirroring for D oc RE : A Self-Supervised Iterative Reflection Framework with Triplet-Centric Explicit and Implicit Feedback

    Han, Xu and Wang, Bo and Sun, Yueheng and Zhao, Dongming and Qu, Zongfeng and He, Ruifang and Hou, Yuexian and Hu, Qinghua. Cognitive Mirroring for D oc RE : A Self-Supervised Iterative Reflection Framework with Triplet-Centric Explicit and Implicit Feedback. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)...

    work page doi:10.18653/v1/2025.xllm-1.18 2025

  43. [43]

    Cross-Document Event-Keyed Summarization

    Walden, William and Kuchmiichuk, Pavlo and Martin, Alexander and Jin, Chihsheng and Cao, Angela and Sun, Claire and Allen, Curisia and White, Aaron. Cross-Document Event-Keyed Summarization. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.19

    work page doi:10.18653/v1/2025.xllm-1.19 2025

  44. [44]

    Transfer of Structural Knowledge from Synthetic Languages

    Budnikov, Mikhail and Yamshchikov, Ivan. Transfer of Structural Knowledge from Synthetic Languages. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.20

    work page doi:10.18653/v1/2025.xllm-1.20 2025

  45. [45]

    Language Models are Universal Embedders

    Zhang, Xin and Li, Zehan and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Zhang, Min. Language Models are Universal Embedders. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.21

    work page doi:10.18653/v1/2025.xllm-1.21 2025

  46. [46]

    D ia DP @ XLLM 25: Advancing C hinese Dialogue Parsing via Unified Pretrained Language Models and Biaffine Dependency Scoring

    Duan, Shuoqiu and Chen, Xiaoliang and Miao, Duoqian and Gu, Xu and Li, Xianyong and Du, Yajun. D ia DP @ XLLM 25: Advancing C hinese Dialogue Parsing via Unified Pretrained Language Models and Biaffine Dependency Scoring. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.22

    work page doi:10.18653/v1/2025.xllm-1.22 2025

  47. [47]

    LLMSR @ XLLM 25: Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation

    Yuan, Jiahao and Sun, Xingzhe and Yu, Xing and Wang, Jingwen and Du, Dehui and Cui, Zhiqing and Di, Zixiang. LLMSR @ XLLM 25: Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.23

    work page doi:10.18653/v1/2025.xllm-1.23 2025

  48. [48]

    S peech EE @ XLLM 25: End-to-End Structured Event Extraction from Speech

    Chaudhuri, Soham and Biswas, Diganta and Saha, Dipanjan and Das, Dipankar and Bandyopadhyay, Sivaji. S peech EE @ XLLM 25: End-to-End Structured Event Extraction from Speech. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.24

    work page doi:10.18653/v1/2025.xllm-1.24 2025

  49. [49]

    Luu, Son and Van Nguyen, Kiet

    Pham Hoang Le, Nguyen and Dinh Thien, An and T. Luu, Son and Van Nguyen, Kiet. D oc IE @ XLLM 25: Z ero S emble - Robust and Efficient Zero-Shot Document Information Extraction with Heterogeneous Large Language Model Ensembles. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.25

    work page doi:10.18653/v1/2025.xllm-1.25 2025

  50. [50]

    D oc IE @ XLLM 25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations

    Popovic, Nicholas and Kangen, Ashish and Schopf, Tim and F. D oc IE @ XLLM 25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.26

    work page doi:10.18653/v1/2025.xllm-1.26 2025

  51. [51]

    LLMSR @ XLLM 25: Integrating Reasoning Prompt Strategies with Structural Prompt Formats for Enhanced Logical Inference

    Tai, Le and Van, Thin. LLMSR @ XLLM 25: Integrating Reasoning Prompt Strategies with Structural Prompt Formats for Enhanced Logical Inference. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.27

    work page doi:10.18653/v1/2025.xllm-1.27 2025

  52. [52]

    D oc IE @ XLLM 25: UIEP rompter: A Unified Training-Free Framework for universal document-level information extraction via Structured Prompt

    Qiu, Chengfeng and Zhou, Lifeng and Wei, Kaifeng and Li, Yuke. D oc IE @ XLLM 25: UIEP rompter: A Unified Training-Free Framework for universal document-level information extraction via Structured Prompt. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.28

    work page doi:10.18653/v1/2025.xllm-1.28 2025

  53. [53]

    LLMSR @ XLLM 25: SWRV : Empowering Self-Verification of Small Language Models through Step-wise Reasoning and Verification

    Chen, Danchun. LLMSR @ XLLM 25: SWRV : Empowering Self-Verification of Small Language Models through Step-wise Reasoning and Verification. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.29

    work page doi:10.18653/v1/2025.xllm-1.29 2025

  54. [54]

    LLMSR @ XLLM 25: An Empirical Study of LLM for Structural Reasoning

    Li, Xinye and Wan, Mingqi and Sui, Dianbo. LLMSR @ XLLM 25: An Empirical Study of LLM for Structural Reasoning. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.30

    work page doi:10.18653/v1/2025.xllm-1.30 2025

  55. [55]

    LLMSR @ XLLM 25: A Language Model-Based Pipeline for Structured Reasoning Data Construction

    Xing, Hongrui and Liu, Xinzhang and Jiang, Zhuo and Yang, Zhihao and Yao, Yitong and Wang, Zihan and Deng, Wenmin and Wang, Chao and Song, Shuangyong and Yang, Wang and He, Zhongjiang and Li, Yongxiang. LLMSR @ XLLM 25: A Language Model-Based Pipeline for Structured Reasoning Data Construction. Proceedings of the 1st Joint Workshop on Large Language Model...

    work page doi:10.18653/v1/2025.xllm-1.31 2025

  56. [56]

    S peech EE @ XLLM 25: Retrieval-Enhanced Few-Shot Prompting for Speech Event Extraction

    Gedeon, M \'a t \'e. S peech EE @ XLLM 25: Retrieval-Enhanced Few-Shot Prompting for Speech Event Extraction. Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025). 2025. doi:10.18653/v1/2025.xllm-1.32

    work page doi:10.18653/v1/2025.xllm-1.32 2025

  57. [57]

    Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  58. [58]

    An introduction to computational identification and classification of Upam \= a alaṇk \= a ra

    Jadhav, Bhakti and Dutta, Himanshu and Kanitkar, Shruti and Kulkarni, Malhar and Bhattacharyya, Pushpak. An introduction to computational identification and classification of Upam \= a alaṇk \= a ra. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  59. [59]

    Aesthetics of S anskrit Poetry from the Perspective of Computational Linguistics: A Case Study Analysis on \'S ikṣ \= a ṣṭaka

    Sandhan, Jivnesh and Barbadikar, Amruta and Maity, Malay and Satuluri, Pavankumar and Sandhan, Tushar and Gupta, Ravi M and Goyal, Pawan and Behera, Laxmidhar. Aesthetics of S anskrit Poetry from the Perspective of Computational Linguistics: A Case Study Analysis on \'S ikṣ \= a ṣṭaka. Computational Sanskrit and Digital Humanities - World Sanskrit Confere...

    2025

  60. [60]

    Itaretara Dvandva: A challenge for Dependency Tree semantics

    Kulkarni, Amba and Neelamana, Vasudha. Itaretara Dvandva: A challenge for Dependency Tree semantics. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  61. [61]

    A Case Study of Handwritten Text Recognition from Pre-Colonial era S anskrit Manuscripts

    Chincholikar, Kartik and Dwivedi, Shagun and Gopalan, Kaushik and Awasthi, Tarinee. A Case Study of Handwritten Text Recognition from Pre-Colonial era S anskrit Manuscripts. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  62. [62]

    Towards Accent-Aware V edic S anskrit Optical Character Recognition Based on Transformer Models

    Tsukagoshi, Yuzuki and Kuroiwa, Ryo and Ohmukai, Ikki. Towards Accent-Aware V edic S anskrit Optical Character Recognition Based on Transformer Models. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  63. [63]

    Vedavani: A Benchmark Corpus for ASR on V edic S anskrit Poetry

    Kumar, Sujeet and Ray, Pretam and Beerukuri, Abhinay and Kamoji, Shrey and Jagadeeshan, Manoj Balaji and Goyal, Pawan. Vedavani: A Benchmark Corpus for ASR on V edic S anskrit Poetry. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  64. [64]

    Compound Type Identification in S anskrit

    Krishnan, Sriram and Satuluri, Pavankumar and Barbadikar, Amruta and Prasanna Venkatesh, T S and Kulkarni, Amba. Compound Type Identification in S anskrit. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  65. [65]

    IKML : A Markup Language for Collaborative Semantic Annotation of I ndic Texts

    Lakkundi, Chaitanya S and Rajaraman, Gopalakrishnan and Susarla, Sai Rama Krishna. IKML : A Markup Language for Collaborative Semantic Annotation of I ndic Texts. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  66. [66]

    Challenges in Processing V edic S anskrit: Towards creating a normalized dataset for the Ṛgveda-saṃhit \= a

    Krishnan, Sriram and Gayathri, Sepuri and Kulkarni, Amba. Challenges in Processing V edic S anskrit: Towards creating a normalized dataset for the Ṛgveda-saṃhit \= a. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  67. [67]

    P \= a ṇḍitya: Visualizing S anskrit Intellectual Networks

    Neill, Tyler. P \= a ṇḍitya: Visualizing S anskrit Intellectual Networks. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  68. [68]

    Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval on E nglish Queries and S anskrit Documents

    Jagadeeshan, Manoj Balaji and Raj, Prince and Goyal, Pawan. Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval on E nglish Queries and S anskrit Documents. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  69. [69]

    Concordance of S anskrit Synonyms

    Patel, Dhaval. Concordance of S anskrit Synonyms. Computational Sanskrit and Digital Humanities - World Sanskrit Conference 2025. 2025

    2025

  70. [70]

    Proceedings of the First Workshop on Writing Aids at the Crossroads of AI, Cognitive Science and NLP (WRAICOGS 2025). 2025

    2025

  71. [71]

    Chain-of- M eta W riting: Linguistic and Textual Analysis of How Small Language Models Write Young Students Texts

    Buhnila, Ioana and Cislaru, Georgeta and Todirascu, Amalia. Chain-of- M eta W riting: Linguistic and Textual Analysis of How Small Language Models Write Young Students Texts. Proceedings of the First Workshop on Writing Aids at the Crossroads of AI, Cognitive Science and NLP (WRAICOGS 2025). 2025

    2025

  72. [72]

    Semantic Masking in a Needle-in-a-haystack Test for Evaluating Large Language Model Long-Text Capabilities

    Shi, Ken and Penn, Gerald. Semantic Masking in a Needle-in-a-haystack Test for Evaluating Large Language Model Long-Text Capabilities. Proceedings of the First Workshop on Writing Aids at the Crossroads of AI, Cognitive Science and NLP (WRAICOGS 2025). 2025

    2025

  73. [73]

    Reading Between the Lines: A dataset and a study on why some texts are tougher than others

    Khallaf, Nouran and Eugeni, Carlo and Sharoff, Serge. Reading Between the Lines: A dataset and a study on why some texts are tougher than others. Proceedings of the First Workshop on Writing Aids at the Crossroads of AI, Cognitive Science and NLP (WRAICOGS 2025). 2025

    2025

  74. [74]

    P ara R ev : Building a dataset for Scientific Paragraph Revision annotated with revision instruction

    Jourdan, L \'e ane and Boudin, Florian and Dufour, Richard and Hernandez, Nicolas and Aizawa, Akiko. P ara R ev : Building a dataset for Scientific Paragraph Revision annotated with revision instruction. Proceedings of the First Workshop on Writing Aids at the Crossroads of AI, Cognitive Science and NLP (WRAICOGS 2025). 2025

    2025

  75. [75]

    Towards an operative definition of creative writing: a preliminary assessment of creativeness in AI and human texts

    Maggi, Chiara and Vitaletti, Andrea. Towards an operative definition of creative writing: a preliminary assessment of creativeness in AI and human texts. Proceedings of the First Workshop on Writing Aids at the Crossroads of AI, Cognitive Science and NLP (WRAICOGS 2025). 2025

    2025

  76. [76]

    Decoding Semantic Representations in the Brain Under Language Stimuli with Large Language Models

    Sato, Anna and Kobayashi, Ichiro. Decoding Semantic Representations in the Brain Under Language Stimuli with Large Language Models. Proceedings of the First Workshop on Writing Aids at the Crossroads of AI, Cognitive Science and NLP (WRAICOGS 2025). 2025

    2025

  77. [77]

    Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH). 2025

    2025

  78. [78]

    A Comprehensive Taxonomy of Bias Mitigation Methods for Hate Speech Detection

    Fillies, Jan and Wawerek, Marius and Paschke, Adrian. A Comprehensive Taxonomy of Bias Mitigation Methods for Hate Speech Detection. Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH). 2025

    2025

  79. [79]

    Sensitive Content Classification in Social Media: A Holistic Resource and Evaluation

    Antypas, Dimosthenis and Sen, Indira and Perez Almendros, Carla and Camacho-Collados, Jose and Barbieri, Francesco. Sensitive Content Classification in Social Media: A Holistic Resource and Evaluation. Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH). 2025

    2025

  80. [80]

    From civility to parity: Marxist-feminist ethics for context-aware algorithmic content moderation

    Oh, Dayei. From civility to parity: Marxist-feminist ethics for context-aware algorithmic content moderation. Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH). 2025

    2025

Showing first 80 references.