📰 INLG 2025: all accepted papers

58 papers · the most cited first · ← INLG 2025

1. ARTIST: A Learning Support System for Fostering Students' Argumentative Writing Skills ↗Thomas Huber, Christina Niklaus · System Demonstrations
2. Analysing Reference Production of Large Language Models ↗Chengzhao Wu, Guanyi Chen, Fahime Same et al.
3. Annotating Hallucinations in Question-Answering using Rewriting ↗Xu Liu, Guanyi Chen, Kees van Deemter et al.
4. Are Multi-Agents the new Pipeline Architecture for Data-to-Text Systems? ↗Chinonso Cynthia Osuji, Brian Timoney, Mark Andrade et al.
5. Assessing Semantic Consistency in Data-to-Text Generation: A Meta-Evaluation of Textual, Semantic and Model-Based Metrics ↗Rudali Huidrom, Michela Lorandi, Simon Mille et al.
6. Automated and Context-Aware Code Documentation Leveraging Advanced LLMs ↗Swapnil Sharma Sarker, Tanzina Taher Ifty
7. Benchmarking and Improving LVLMs on Event Extraction from Multimedia Documents ↗Fuyu Xing, Zimu Wang, Wei Wang et al.
8. CSPaper Review: Fast, Rubric-Faithful Conference Feedback ↗Lele Cao, Lei You, R&D Team · System Demonstrations
9. Can GPT models Follow Human Summarization Guidelines? A Study for Targeted Communication Goals ↗Yongxin Zhou, Fabien Ringeval, François Portet
10. Can LLMs Help Encoder Models Maintain Both High Accuracy and Consistency in Temporal Relation Classification? ↗Adiel Meir, Kfir Bar
11. Cognitive Flow: An LLM-Automated Framework for Quantifying Reasoning Distillation ↗José Matos, Catarina Silva, Hugo Gonçalo Oliveira
12. Counterfactual Simulatability of LLM Explanations for Generation Tasks ↗Marvin Limpijankit, Yanda Chen, Melanie Subbiah et al.
13. DCU-ADAPT-modPB at the GEM'24 Data-to-Text Task: Analysis of Human Evaluation Results ↗Rudali Huidrom, Chinonso Cynthia Osuji, Kolawole John Adebayo et al.
14. Do My Eyes Deceive Me? A Survey of Human Evaluations of Hallucinations in NLG ↗Patricia Schmidtova, Eduardo Calò, Simone Balloccu et al.
15. Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation ↗Tomasz Limisiewicz, David Mareček, Tomáš Musil
16. Echoes of Others: Real-Time LLM Dialogue Generation for Immersive NPC Interaction ↗James McGrath, Michela Lorandi, Anya Belz · System Demonstrations
17. Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models ↗Cong Thanh Do, Rama Sanand Doddipatla, Kate Knill
18. Enhancing Coherence and Interestingness in Knowledge-Grounded Dialogue Generation ↗Hiroki Onozeki, Michimasa Inaba
19. Enhancing Named Entity Translation from Classical Chinese to Vietnamese in Traditional Vietnamese Medicine Domain: A Hybrid Masking and Dictionary-Augmented Approach ↗Nhu Pham, Uyen Nguyen, Long Nguyen et al.
20. Evaluating LLM-Generated Versus Human-Authored Responses in Role-Play Dialogues ↗Dongxu Lu, Johan Jeuring, Albert Gatt
21. Evaluating LLMs' Ability to Understand Numerical Time Series for Text Generation ↗Mizuki Arai, Tatsuya Ishigaki, Masayuki Kawarada et al.
22. Exploring the Power of Large Language Models for Vietnamese Implitcit Sentiment Analysis ↗Huy Gia Luu, Dang Van Thin
23. Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking ↗Daniel Russo, Stefano Menini, Jacopo Staiano et al.
24. FinStat2SQL: A Text2SQL Pipeline for Financial Statement Analysis ↗Hung Quang Nguyen, Anh Phuong Trinh, Hung Phan Quoc Mai et al.
25. Fine-Tuning, Prompting and RAG for Knowledge Graph-to-Russian Text Generation. How do these Methods generalise to Out-of-Distribution Data? ↗Anna Nikiforovskaya, William Soto-Martinez, Evan Chapple et al.
26. Forecasting Conversation Derailments Through Generation ↗Yunfan Zhang, Kathleen McKeown, Smaranda Muresan
27. FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation ↗Kristýna Onderková, Ondrej Platek, Zdeněk Kasner et al.
28. From Prototypical to Relational: How LLMs Navigate Complex Analogies ↗Mayukh Das, Wolf-Tilo Balke
29. Generating Impact and Critique Explanations of Predictions made by a Goal Recognizer ↗Jair da Silva Ferreira Junior, Ingrid Zukerman, Enes Makalic et al.
30. German4All – A Dataset and Model for Readability-Controlled Paraphrasing in GermanMiriam Anschütz, Thanh Mai Pham, Eslam Nasrallah et al.our summary
31. How (un)faithful are explainable LLM-based NLG metrics? ↗Alex Terentowicz, Mateusz Lango, Ondrej Dusek
32. Human ratings of LLM response generation in pair-programming dialogue ↗Cecilia Domingo, Paul Piwek, Michel Wermelinger et al.
33. Incorporating Formulaicness in the Automatic Evaluation of Naturalness: A Case Study in Logic-to-Text Generation ↗Eduardo Calò, Guanyi Chen, Elias Stengel-Eskin et al.
34. Input Matters: Evaluating Input Structure's Impact on LLM Summaries of Sports Play-by-Play ↗Barkavi Sundararajan, Somayajulu Sripada, Ehud Reiter
35. KDA: Knowledge Distillation Adapter for Cross-Lingual Transfer ↗Ta-Bao Nguyen, Nguyen-Phuong Phan, Tung Le et al.
36. Live Commentary Planning and Generation ↗Chung-Chi Chen, Huan-Wen Ho, Yu-Yu Chang et al.
37. Live Football Commentary (LFC): A Large-Scale Dataset for Building Football Commentary Generation Models ↗Taiga Someya, Tatsuya Ishigaki, Hiroya Takamura
38. LogitRouter: a novel Attention variant for reducing Myopic Routing in Mixture of Experts ↗Felipe Rodriguez, Marcelo Mendoza
39. Mining Contextualized Visual Associations from Images for Creativity Understanding ↗Ananya Sahu, Amith Ananthram, Kathleen McKeown
40. Natural Language Translation of Formal Proofs through Informalization of Proof Steps and Recursive Summarization along Proof Structure ↗Seiji Hattori, Takuya Matsuzaki, Makoto Fujiwara
41. OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs ↗Ivan Kartac, Mateusz Lango, Ondrej Dusek
42. PRICoT: Principle Retrieval and Injection from Inference Successes and Failures for CoT Improvement ↗Yudai Yamazaki, Naoto Takeda, Yasutaka Nishimura et al.
43. QCoder Benchmark: Bridging Language Generation and Quantum Hardware through Simulator-Based Feedback ↗Taku Mikuriya, Tatsuya Ishigaki, Masayuki Kawarada et al.
44. References Matter: Investigating the Impact of Reference Set Variation on Summarization Evaluation ↗Silvia Casola, Yang Janet Liu, Siyao Peng et al.
45. Restaurant Menu Categorization at Scale: LLM-Guided Hybrid Clustering ↗Seemab Latif, Ashar Mehmood, Selim Turki et al.
46. SWI: Speaking with Intent in Large Language Models ↗Yuwei Yin, Eunjeong Hwang, Giuseppe Carenini
47. Scaling Up Data-to-Text Generation to Longer Sequences: A New Dataset and Benchmark Results for Generation from Large Triple Sets ↗Chinonso Cynthia Osuji, Simon Mille, Ornait O'Connell et al.
48. Statistical Multicriteria Evaluation of LLM-Generated Text ↗Esteban Garces Arias, Hannah Blocher, Julian Rodemann et al.
49. Surprisal reveals diversity gaps in image captioning and different scorers change the story ↗Nikolai Ilinykh, Simon Dobnik
50. Taming the Titans: A Survey of Efficient LLM Inference Serving ↗Ranran Zhen, Juntao Li, Yixin Ji et al.
51. Team SaarLST at the GEM'24 D2T Task: Symbolic retrieval substantially reduces hallucination in data-to-text generation ↗Mayank Jobanputra, Vera Demberg
52. The 2024 GEM Shared Task on Multilingual Data-to-Text Generation: English and Spanish Qualitative Evaluation Results ↗João Sedoc, Simon Mille, Miruna Adriana Clinciu et al.
53. Towards Trustworthy Lexical Simplification: Exploring Safety and Efficiency with Small LLMs ↗Akio Hayakawa, Stefan Bott, Horacio Saggion
54. Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals ↗Qianli Wang, Van Bach Nguyen, Nils Feldhus et al.
55. ViNumFCR: A Novel Vietnamese Benchmark for Numerical Reasoning Fact Checking on Social Media News ↗Nhi Ngoc-Phuong Luong, Anh Thi-Lan Le, Tin Van Huynh et al.
56. VitaEval: Open-source Human Evaluation Tool for Video-to-Text and Video-to-Audio Systems ↗Goran Topic, Yuki Saito, Katsuhito Sudoh et al. · System Demonstrations
57. When LLMs Can't Help: Real-World Evaluation of LLMs in Nutrition ↗Karen Jia-Hui Li, Simone Balloccu, Ondrej Dusek et al.
58. Who's Laughing Now? An Overview of Computational Humour Generation and Explanation ↗Tyler Loakman, William Thorne, Chenghua Lin

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/inlg/2025/papers/