---
title: "GEM 2026 — all accepted papers with summaries and citations"
description: "All 76 papers of GEM 2026, the most cited first; those with our summary link to it. Among them: An Empirical Study of LLM-as-a-Judge: How…"
canonical: "https://research.elamur.ai/free/en/venues/gem/2026/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/gem/2026/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [GEM](https://md.research.elamur.ai/free/en/venues/gem/) / [2026](https://md.research.elamur.ai/free/en/venues/gem/2026/) / papers

# GEM 2026: all accepted papers

76 papers · the most cited first · [← GEM 2026](https://md.research.elamur.ai/free/en/venues/gem/2026/)

1. **[An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability ↗](https://aclanthology.org/2026.gem-main.19/)**Yusuke Yamauchi, Taro Yano, Masafumi Oyamada*3 citations*
2. **[Capturing Epistemic Uncertainty in LLM-Based Soft Labeling ↗](https://aclanthology.org/2026.gem-main.21/)**Yanru Jiang, Siyu Liang*1 citation*
3. **[MedFact: Benchmarking the Fact-Checking Capabilities of Large Language Models on Chinese Medical Texts ↗](https://aclanthology.org/2026.gem-main.59/)**Jiayi He, Yangmin Huang, Qianyun Du et al.*1 citation*
4. **[MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022–2025) ↗](https://aclanthology.org/2026.gem-main.71/)**Paolo Pedinotti, Peter Baumann, Nathan Jessurun et al.*1 citation*
5. **[Permutation-Consensus Listwise Judging for Robust Factuality Evaluation ↗](https://aclanthology.org/2026.gem-main.58/)**Tianyi Huang, Nathan Huang, Justin Tang et al.*1 citation*
6. **[Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses ↗](https://aclanthology.org/2026.gem-main.9/)**Xanh Ho, Jiahao Huang, Florian Boudin et al.*1 citation*
7. **[Who Endorsed It? Measuring Authority Bias Across Expertise Levels in Language Models ↗](https://aclanthology.org/2026.gem-main.75/)**Priyanka Mary Mammen, Emil Joswin, Shankar Venkitachalam*1 citation*
8. **[A Progressive Evaluation Framework for Multicultural Analysis of Story Visualization ↗](https://aclanthology.org/2026.gem-main.39/)**Janak Kapuriya, Ali Hatami, Paul Buitelaar
9. **[Are LLM Benchmarks Already Contaminated? A Systematic Review of Contamination Detection Methods ↗](https://aclanthology.org/2026.gem-main.50/)**Erfan Nourbakhsh, Mohammad Sadegh Sirjani, Amir Mousavi et al.
10. **[C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning ↗](https://aclanthology.org/2026.gem-main.62/)**Avni Mittal, Rauno Arike
11. **[CoSy: Conversational Synthesis for Grounded Question Answering ↗](https://aclanthology.org/2026.gem-main.2/)**Patrick Huber, Arash Einolghozati, Rylan Conway et al.
12. **[Complex-IF and Beyond: Expert Rubrics for RLVR ↗](https://aclanthology.org/2026.gem-main.61/)**Sushant Mehta, Liudas Panavas, Eleanor Fleming et al.
13. **[Component Transfer Can Exceed Full Model Performance: Investigating Post-Trained Mixture-of-Experts ↗](https://aclanthology.org/2026.gem-main.7/)**Rabin Tiwari
14. **[Concord: An Agreement-Aware Multi-Adjudication Pipeline for LLM Evaluation ↗](https://aclanthology.org/2026.gem-main.46/)**Tyler Bliss, Mahit Verma, Aila Iyer-Singh et al.
15. **[Cross-Domain Semantic Fidelity Evaluation for Meaning-to-Text Generation ↗](https://aclanthology.org/2026.gem-main.41/)**Davan Harrison, Marilyn Walker
16. **[Do Nugget-Based Evaluation Patterns Generalize to List-QA? ↗](https://aclanthology.org/2026.gem-main.84/)**MohammadJavad Ardestani, Ehsan Kamalloo, Davood Rafiei
17. **[E-star 12B: Reliable Rubric-Following and Domain-Adaptive SLM Evaluator for Korean Industrial Settings ↗](https://aclanthology.org/2026.gem-main.42/)**Yonghoon Kwon, Heondeuk Lee, Barom Kang
18. **[Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debate ↗](https://aclanthology.org/2026.gem-main.60/)**Ali Keramati, Justin Cheok, Jacob Horne et al.
19. **[EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments ↗](https://aclanthology.org/2026.gem-main.67/)**Zefang Liu, Yinzhu Quan
20. **[Evaluating ASR Quality at Scale on TV Entertainment Platforms ↗](https://aclanthology.org/2026.gem-main.35/)**Adeep Hande, Kishorekumar Sundararajan, Yidnekachew Endale et al.
21. **[Evaluating Counterfactual Strategic Reasoning in Large Language Models ↗](https://aclanthology.org/2026.gem-main.31/)**Dimitrios Georgousis, Maria Lymperaiou, Angeliki Dimitriou et al.
22. **[Evaluating Multilingual Sentiment Classifiers Using an LLM-Annotated Wikipedia Benchmark ↗](https://aclanthology.org/2026.gem-main.63/)**Milena Stróżyna, Włodzimierz Lewoniewski, Izabela Czumałowska
23. **[Evaluating the Reliability of LLMs in Faithfully Updating Text: An Empirical Study ↗](https://aclanthology.org/2026.gem-main.28/)**Ayan Datta, Paheli Bhattacharya, Rishabh Gupta
24. **[Exploring Coherence of LLMs in Multilingual Question Answering ↗](https://aclanthology.org/2026.gem-main.52/)**Stefano Campese, Ivano Lauriola
25. **[Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge ↗](https://aclanthology.org/2026.gem-main.37/)**Zhuoyi Yang, Yurun Song, Kyler G. Harris et al.
26. **[ISO-Bench: Benchmarking Multimodal Causal Reasoning in Visual–Language Models through Procedural Plans ↗](https://aclanthology.org/2026.gem-main.68/)**Ananya Sadana, Yash Kumar Lal, Jiawei Zhou
27. **[Identifying Where Large Language Models Struggle in Answering Complex Questions ↗](https://aclanthology.org/2026.gem-main.11/)**Xanh Ho, Florian Boudin, Saku Sugawara et al.
28. **[IndicMMLU-Pro: Benchmarking Indic Large Language Models on Multi-Task Language Understanding ↗](https://aclanthology.org/2026.gem-main.10/)**Sankalp Jajee, Ashutosh Kumar, Nikunj Kotecha et al.
29. **[Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization ↗](https://aclanthology.org/2026.gem-main.40/)**Long Chen, Ryan Razkenari, Yuxuan Zhou et al.
30. **[Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities ↗](https://aclanthology.org/2026.gem-main.65/)**Nikita Tatarinov, Siddhant Sukhani, Agam Shah et al.
31. **[Lost in Space: Finding the Right Tokens for Structured Output ↗](https://aclanthology.org/2026.gem-main.18/)**Sil Hamilton, David Mimno
32. **[MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following ↗](https://aclanthology.org/2026.gem-main.23/)**Jaeyun Lee, Junyoung Koh, Zeynel Tok et al.
33. **[MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models ↗](https://aclanthology.org/2026.gem-main.38/)**Weixin Liu, Congning Ni, Shelagh A. Mulvaney et al.
34. **[Mapping Out the NLP Evaluation Landscape with a Standard Taxonomy of Quality Criteria ↗](https://aclanthology.org/2026.gem-main.77/)**Anya Belz, Simon Mille, Craig Thomson
35. **[MedAct: Removing the Human Bottleneck in Benchmarking Clinical LLM Safety ↗](https://aclanthology.org/2026.gem-main.24/)**Arjun Krishna, Brian Pridgen, Max Silverstein
36. **[Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results](https://md.research.elamur.ai/free/en/papers/peter-2026-mind-gap-or-not-how/)**Jan-Thorsten Peter, David Vilar, Tobias Domhan et al.*our summary*
37. **[More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs ↗](https://aclanthology.org/2026.gem-main.12/)**Marina Igitkhanian, Erik Arakelyan
38. **[NanoFlux: Adversarial Dual-LLM Evaluation and Distillation for Multi-Domain Reasoning ↗](https://aclanthology.org/2026.gem-main.27/)**Raviteja Anantha, Soheil Hor, Teodor Nicola Antoniu et al.
39. **[Near-Miss: Latent Policy Failure Detection in Agentic Workflows ↗](https://aclanthology.org/2026.gem-main.30/)**Ella Rabinovich, David Boaz, Naama Zwerdling et al.
40. **[Not All Tokens Are Equal: Per-Dimension Top-K Pooling for Adversarially Robust BERT Classification ↗](https://aclanthology.org/2026.gem-main.29/)**Manoranjan Dash, Shivam Anand Aralikatti, Shanay Sheth et al.
41. **[Position: A Semiotic-Hermeneutic Approach to Evaluating Meaning in LLM Summaries via the Inductive Conceptual Rating Metric ↗](https://aclanthology.org/2026.gem-main.81/)**Natalie Perez, Sreyoshi Bhaduri, Aman Chadha
42. **[Position: Evaluation Scores Are Perishable Knowledge Claims ↗](https://aclanthology.org/2026.gem-main.80/)**Sankalp Gilda, Shlok Gilda
43. **[Position: Scores Without Context? Rethinking the Role of Evaluation in the Era of LLMs ↗](https://aclanthology.org/2026.gem-main.82/)**Jiawei Zhou
44. **[Position: Toward a Metric Typology for Language Model Evaluation ↗](https://aclanthology.org/2026.gem-main.78/)**Jasper Kyle Catapang
45. **[Position: What Are We Measuring? Rethinking Evaluation in Natural Language Generation ↗](https://aclanthology.org/2026.gem-main.79/)**Wajdi Zaghouani
46. **[Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations ↗](https://aclanthology.org/2026.gem-main.43/)**Sachin Kumar
47. **[Process Standardisation for Human Evaluation of NLP System Outputs ↗](https://aclanthology.org/2026.gem-main.64/)**Craig Thomson, Javier González Corbelle, Anya Belz
48. **[RBCorr: Response Bias Correction in Language Models ↗](https://aclanthology.org/2026.gem-main.51/)**Om Bhatt, Anna A Ivanova
49. **[RE-AD: Real-Time Requirement Adherence for Data Labeling ↗](https://aclanthology.org/2026.gem-main.17/)**Siddarth Malreddy, Ishan Nigam, Akshay Arora et al.
50. **[Reference Games as a Testbed for the Alignment of Model Uncertainty and Clarification Requests ↗](https://aclanthology.org/2026.gem-main.76/)**Manar Ali, Judith Sieker, Sina Zarrieß et al.
51. **[Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents ↗](https://aclanthology.org/2026.gem-main.13/)**Anh Ta, Junjie Zhu, Shahin Shayandeh
52. **[ReproHum \#0031–01: Reproducing a Human Readability Evaluation for Question–Answer Generation Systems ↗](https://aclanthology.org/2026.gem-main.88/)**Manuela Hürlimann, Mark Cieliebak
53. **[ReproHum \#0033-05: Human Evaluation Report on “Generating Scientific Definitions with Controllable Complexity” ↗](https://aclanthology.org/2026.gem-main.89/)**Ines Arous, Jackie Chi Kit Cheung
54. **[ReproHum \#0124-03: Reproducing Human Scores on Neural REG Models ↗](https://aclanthology.org/2026.gem-main.86/)**Maurice Langner
55. **[ReproHum \#0669-08: Reproducing a Recipe for Arbitrary Text Style Transfer with LLMs](https://md.research.elamur.ai/free/en/papers/mahamood-2026-reprohum-0669-08-reproducing-recipe/)**Saad Mahamood*our summary*
56. **[ReproHum \#0866-04: Variability in Human Judgments of Sociopolitical Acceptability Across Studies ↗](https://aclanthology.org/2026.gem-main.87/)**Rui Fan, Guanyi Chen
57. **[ReproNLP 2026: A Third Replication of the Human Evaluation of a QAG System for Children's Storybooks ↗](https://aclanthology.org/2026.gem-main.85/)**Marcel Mroczek, Chiara Albarello, Paul-Emmanuel Floch et al.
58. **[Response Content Units: Evaluating Completeness and Proactiveness in Medical Open-Response Question Answering ↗](https://aclanthology.org/2026.gem-main.25/)**Yongsin Park, Wen-wai Yim, Emma McKibbin et al.
59. **[SAUCE: Summary Analysis Using Conversation Entailment ↗](https://aclanthology.org/2026.gem-main.34/)**Man-Ling Sung, Hemanth Kandula, Jeff Ma et al.
60. **[Self-Anchoring Calibration Drift in Large Language Models: How Multi-Turn Conversations Reshape Model Confidence ↗](https://aclanthology.org/2026.gem-main.4/)**Harshavardhan
61. **[Semantic vs. Structural Signals: Log-Probability and LLM-as-a-Judge for Reference-Free Code Evaluation ↗](https://aclanthology.org/2026.gem-main.55/)**Dmitriy Fedrushkov, Yulong He, Ivan Smirnov et al.
62. **[Speculative Refinement: A Hybrid Autoregressive Diffusion Decoding Strategy and Its Behavior Across Benchmarks ↗](https://aclanthology.org/2026.gem-main.33/)**Aditi Gupta, Neel Mishra, Kushagra Trivedi et al.
63. **[Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges ↗](https://aclanthology.org/2026.gem-main.57/)**Srimonti Dutta, Akshata Kishore Moharir
64. **[Sycophancy Negatively Affects LLM-as-a-Judge in Conflict Evaluation ↗](https://aclanthology.org/2026.gem-main.45/)**Naghmeh Farzi, Laura Dietz, Samuel Carton
65. **[TSAQA: Time Series Analysis Question And Answering Benchmark ↗](https://aclanthology.org/2026.gem-main.74/)**Baoyu Jing, Sanhorn Chen, Lecheng Zheng et al.
66. **[Teaching Values to Machines: Simulating Human-Like Behavior in LLMs ↗](https://aclanthology.org/2026.gem-main.70/)**Asaf Yehudai, Naama Rozen, Ariel Gera
67. **[Temporal Tokenization Strategies for Event Sequence Modeling with Large Language Models ↗](https://aclanthology.org/2026.gem-main.5/)**Zefang Liu, Nam H Nguyen, Yinzhu Quan et al.
68. **[Text Analytics Evaluation Framework: A Case Study on LLMs and Social Media ↗](https://aclanthology.org/2026.gem-main.69/)**Yuefeng Shi, Nedjma Ousidhoum, Jose Camacho-Collados
69. **[The Shared Task on Reproducibility of Evaluations in NLP (ReproNLP) 2026: Overview and Results ↗](https://aclanthology.org/2026.gem-main.83/)**Anya Belz, Craig Thomson, Javier González Corbelle
70. **[The Silent Vote: Improving Zero-Shot LLM Reliability by Aggregating Semantic Neighborhoods ↗](https://aclanthology.org/2026.gem-main.48/)**Sanket Badhe, Priyanka Tiwari, Deep Shah
71. **[Token Cost Inequality: Measuring Tokenization Disparities Across Scripts in Roman Urdu and Urdu ↗](https://aclanthology.org/2026.gem-main.54/)**Waleed Jamil, Saima Rafi, Yanchao Yu
72. **[Tool-Aware Planning for Contact-Center Analytics: Evaluating LLMs through Lineage-Guided Query Decomposition ↗](https://aclanthology.org/2026.gem-main.73/)**Varun Nathan, Shreyas Guha, Ayush Kumar
73. **[VAIDYA: Validated Agents for Intelligent Diagnosis and Yielded Analysis ↗](https://aclanthology.org/2026.gem-main.3/)**Kalash Shah, Gautam Bhutani, Rohitaswa Sarbhangia et al.
74. **[When Users Are Happy but Agents Are Wrong: Multi-Dimensional Evaluation of Tool-Augmented Dialogue ↗](https://aclanthology.org/2026.gem-main.72/)**Tanya Shourya, Yingfan Wang, Zhaoyi Joey Hou et al.
75. **[WildIFEval: Instruction Following in the Wild ↗](https://aclanthology.org/2026.gem-main.66/)**Gili Lior, Asaf Yehudai, Ariel Gera et al.
76. **[“Be My Cheese?”: Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs ↗](https://aclanthology.org/2026.gem-main.6/)**Madison Van Doren, Casey Ford, Jennifer Barajas et al.
- [← back to](https://md.research.elamur.ai/free/en/venues/gem/2026/) — GEM 2026