United States

We describe our system for SemEval-2026 Task 13, Subtask B: code classification into 11 categories (human-written or generated by one of 10 LLM families). The task presents extreme class imbalance and distribution shift across multiple generators provided in the dataset (31 in training, 59 in test, with 36 unseen). On that focus, we approached with two components: (1) UniXcoder as the encoder with Label-Distribution-Aware Margin (LDAM) loss for handling class imbalance, which provides a +7% absolute improvement over the cross-entropy baseline; and (2) a diverse ensemble of 12 models trained with different objectives and architectures which is detailed in the appendix, combined with hard voting. Our system achieves 41.28% Macro F1 on the official test set. We find that loss engineering and ensemble diversity matter more than domain adaptation techniques, which consistently degraded test performance.

ACL 2026

Codexa at SemEval-2026 Task 13: Loss Engineering and Diverse Ensemble Strategies for Multi-Class Code Authorship Attribution

code authorship attribution

machine-generated code detection

distribution shift

ensemble learning

class imbalance

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. <br>
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) <br><br><br>
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>
<br><br><br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to ACL 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

workshop paper

We present the results and the main findings of SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios. Our task featured three subtasks. Subtask A is a binary classification task
that determines whether a given code snippet is written by a human or generated by a machine. This subtask focuses on the development of robust methods for AI-generated code identification, since the training and the test data splits have code in different languages and cover diverse usage domains. Subtask B focuses on defining synthetic code smells and requires participants to identify the provenance of the generator family of the model that generated the given code snippet. Subtask C aims at more fine-grained attribution of the written code: whether it was fully AI-generated, fully human-written, produced in human-AI collaboration (hybrid) or by a model tuned or prompted to give human-like code. The task attracted a large number of team members: subtask A (81), subtask B (34), and subtask C (32). In this study, we present the task, analyze the results and discuss the submissions of the system and the methods they used.

SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios

We present SemEval-2026 Task 9, a shared task on online polarization detection, covering 22 languages and comprising over 110K annotated instances. Each data instance is multi-labeled with the presence of polarization, polarization type, and polarization manifestation. Participants were asked to predict labels in three subtasks: (1) detecting the presence of polarization, (2) identifying the type of polarization, and (3) recognizing the polarization manifestation. The three tasks attracted over 1,000 participants worldwide and more than 10k submissions on Codabench. We received final submissions from 67 teams and 69 system description papers. We report the baseline results and analyze the performance of the best-performing systems, highlighting the most common approaches and the most effective methods across different subtasks and languages. The dataset and other resources for this task are publicly available.

SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization

This paper presents our system developed for the SemEval-2026 Task 10: PsyCoMark Psycholinguistic Conspiracy Marker Extraction and Detection. on Subtask 1: Conspiracy Marker Extraction. on Subtask 2: Conspiracy Detection. To this end, we focus on English language use four different pre-trained languages models: models–distilbert–distilbert-base uncased, models–distilbert–distilbert-base-multilingual-cased, models–lxyuan–distilbert-base-multilingual-cased-sentiments-student, and models–microsoft–deberta-v3-base. We experiment with 1) the training set data is analyzed visually, 2) use the gemma-3-27b-it generative model to perform data augmentation on the training dataset through prompts for Subtask 2: Conspiracy Detection, and 3) multiple numbers of single models are trained on the training set data. We further study the influence of different hyperparameters on the single model and select the best single model for the prediction of the test set. Our submission achieved the good ranking place in the test set leaderboard. For Subtask 1, the evaluation criteria for this task mainly consist of the aggregate results of the four markers: Actor, Action, Effect, and Victim, and they are measured using the Macro F1 score. For Subtask 2, this task is essentially a binary classification task for text. Performance will be evaluated using macro-averaged F1 score. In other words, this subtask evaluated using Weighted F1 score across different sentences and cultural contexts. For Subtask 1 and Subtask 2, our best approach is to obtain the results are Macro F1 score 0.1587 and Weighted F1 score 0.7411 separately. For the final ranking, organizers will use the aggregate results of Macro F1 score and Weighted F1 score. Even so, our approach has yielded good results.

wangkongqiang at SemEval-2026 Task 10: PsyCoMark- Psycholinguistic Conspiracy Marker Extraction and Detection

This paper describes the system developed by team for SemEval-2026 Task 2, Subtask 1: Longitudinal Affect Assessment. Our goal is to predict Valence and Arousal from ecological essays and feeling words over time. We propose an efficient hybrid framework that uses quantized 7B-scale language models as deterministic meta-feature extractors and combines them with an ensemble of DeBERTa, RoBERTa, and DistilBERT encoders. The system is designed to run on a single consumer-grade RTX 5060 Ti (16GB) GPU while remaining competitive. To bridge discrete supervision and continuous evaluation, we train the model as an ordinal classification problem and decode class probabilities into continuous scores through expected-value decoding. Our best system achieved an overall V&A average of 0.587, with per-dimension composite correlations of 0.647 for Valence and 0.527 for Arousal, ranking 3rd out of 31 teams. The results show that lightweight SLM-derived priors and multi-encoder fusion provide a strong performance--efficiency trade-off, especially for Arousal, where contextual anchoring is crucial.

cclin at SemEval-2026 Task 2 : SLM-Enhanced Lightweight Multi-BERT Ensemble for Longitudinal Affect Assessment

Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits. We propose a training-free hybrid retrieval pipeline for SemEval-2026 Task 8 that combines dense and sparse retrieval with controlled query rewriting and cross-encoder reranking. Our system achieves 0.5453 nDCG@5 on the official test set of Task A, ranking 3rd out of 38 teams and outperforming the strongest baseline (0.4795). For Task C, we reuse the Task A retrieved documents in a lightweight generation pipeline based on the official prompt, achieving 0.5312 (harmonic mean of quality and faithfulness) and ranking 15th out of 29 teams. All retrieval components are open-source, while rewriting and generation use LLM APIs. Code and scripts are available on GitHub (https://github.com/mengsifei/Multi_turn_RAG).

Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG

We describe our research to SemEval-2026 Task 4 on Narrative Story Similarity and Narrative Representation Learning (NSNRL). The shared task defines narrative similarity through comparative judgments over triples consisting of an anchor story and two candidates, where systems determine which candidate is narratively closer (Track A), and must output story embeddings whose cosine distances reproduce the same ordering under withheld evaluation triples (Track B). We implement a unified representation-learning approach based on a Sentence-BERT bi-encoder trained with triple-derived metric learning objectives, combining in-batch contrastive learning with explicit triplet and margin-ranking constraints. Track A is solved by direct cosine comparison between the anchor embedding and each candidate embedding, while Track B outputs normalized story vectors from the same encoder without any additional test-time modelling. During evaluation, we achieve 65.00% accuracy on Track A and 65.50% on Track B. These results suggest that a single, well-aligned bi-encoder can perform competitively across both tracks while remaining computationally efficient.

MarSan at SemEval-2026 Task 4: Narrative Similarity via Sentence-BERT Metric Learning with Triple-Derived Losses

Team PICT's submission for SemEval-2026 Task 3 (DimASR) tackles continuous valence and arousal prediction by heavily focusing on variance reduction and avoiding cross-domain negative transfer. We built strictly domain-isolated pipelines for the Laptop and Restaurant datasets using a RoBERTa-Large backbone. Our architecture extracts a rich feature hierarchy using weighted layer pooling, isolates local context with a [CLS]-driven aspect-aware attention module, and maps to the continuous space using a deep residual regression head. Regularized via R-Drop and SWA, our system achieved 3rd place in the Restaurant domain (RMSE: 1.195) and 9th in the Laptop domain (RMSE: 1.326).

PICT at SemEval-2026 Task 3: A Transformer-Based System for Dimensional Aspect-Aware Sentiment Regression with Weighted Layer Pooling

This paper presents our system developed for SemEval-2026 Task 2. The task requires modeling both current affect and short-term affective change in chronologically ordered user-generated texts. We explore three complementary approaches: (1) LLM prompting under user-aware and user-agnostic settings, (2) a pairwise Maximum Entropy (MaxEnt) model with Ising-style interactions for structured transition modeling, and (3) a lightweight neural regression model incorporating recent affective trajectories and trainable user embeddings. Our findings indicate that LLMs effectively capture static affective signals from text, whereas short-term affective variation in this dataset is more strongly explained by recent numeric state trajectories than by textual semantics.

UKP_Psycontrol at SemEval-2026 Task 2: Modeling Valence and Arousal Dynamics from Text

We present Paradise, our system for SemEval-2026 Task 12: Abductive Event Reasoning, which identifies plausible direct causes of real-world English-language events using retrieved contextual documents. Our approach employs Qwen2.5-7B-Instruct, a 7-billion-parameter instruction-tuned language model combined with carefully engineered chain-of-thought prompting, requiring no task-specific fine-tuning or training-data supervision (prompt components were selected using the development set). The system achieves a score of 0.79 on the official 612-instance test set by integrating explicit causal-inference rules, 4,000-character document context windows, and greedy decoding. Analysis reveals that conservative prediction patterns, 87.1% single-label and 36.9% Option D, effectively exploit the asymmetric scoring metric. Ablation studies confirm that document context contributes +6.4 points, chain-of-thought reasoning +5.3 points, and explicit causal rules +3.1 points to development performance. Our code is publicly available at https://github.com/DhruvGoyal404/semeval2026-task12.

Paradise at SemEval-2026 Task 12: Leveraging Instruction-Tuned Large Language Models with Chain-of-Thought Prompting for Abductive Event Reasoning

This paper introduces a simple approach for predicting how plausible a word sense is in short narratives where meaning is ambiguous. We use 13 hand-crafted features, including text statistics, word-level similarity computed using basic set-based comparisons, and measures of annotator disagreement. Five diverse and largely independent traditional machine learning models are combined using a weighted ensemble with minimal tuning. Despite theoretical grounding in classical disambiguation methods, our system achieves essentially random performance, with Spearman correlation (ρ) of −0.038 and accuracy within standard deviation of 0.542 on the official test set. This result demonstrates that surface-level lexical features, while interpretable, are insufficient for graded sense plausibility prediction without deep semantic representations. By selecting features inspired by classical word sense disambiguation techniques and incorporating signals derived from human disagreement, our model produces plausibility predictions that are largely interpretable. This negative result provides important baselines and insights for future work on graded word sense disambiguation.

Downloads

Next from ACL 2026

SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios

Similar lecture

Team Yuvan at SemEval-2026 Task 13: Task-Adaptive Ensemble Strategies for AI-Generated Code Detection

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2026

SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios

Similar lecture

Team Yuvan at SemEval-2026 Task 13: Task-Adaptive Ensemble Strategies for AI-Generated Code Detection

Downloads