United States

Expert pruning is a practical deployment technique for Mixture-of-Experts (MoE) models. It reduces resource usage and mitigates expert redundancy, but its success depends strongly on the calibration set used for pruning. In domain-general settings, it is unclear which properties of the calibration data drive good pruning outcomes, and the effects of calibration perturbations are often unintuitive. We observe, for example, that calibration sets in different languages can lead to very similar pruning results despite appearing dissimilar on the surface.
To address this, we propose Expert Calibration Lens, a lightweight analysis tool that compares expert activation patterns across datasets to predict the impact of calibration perturbations without repeatedly running expensive pruning procedures. We use activations that are quick to compute and evaluate the resulting analysis for downstream task performance.

ACL 2026

Expert Calibration Lens for Pruning Mixture of Experts

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

demo

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. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<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>

To access this event page, you need to log in with the **email address you registered with**. 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.

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.

Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task re-execution in complex scenarios. We propose AgentFactory, a new self-evolution paradigm that preserves successful task solutions as executable subagent code rather than textual experience. Crucially, these subagents are continuously refined based on execution feedback, becoming increasingly robust and efficient as more tasks are encountered. Saved subagents are pure Python code with standardized documentation, enabling portability across any Python-capable system. We demonstrate that AgentFactory enables continuous capability accumulation: its library of executable subagents grows and improves over time, progressively reducing the effort required for similar tasks without manual intervention. Our implementation is open-sourced at \url{https://github.com/zzatpku/AgentFactory}, and our demonstration video is available at \url{https://youtu.be/iKSsuAXJHW0}.

AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse

We introduce GameDAI, a hierarchical multi-agent framework that transforms instructor-provided questions into fully playable, pedagogically grounded educational games validated through formal mechanic contracts. Built on phase-based LangGraph sub-graphs, deterministic Quality Gates, and structured Pydantic schemas, GameDAI supports two template families encompassing 15 interaction mechanics across spatial reasoning, procedural execution, and higher-order Bloom's Taxonomy objectives.
Evaluated on 200 questions spanning five subject domains, the system achieves a 90% validation pass rate, 98.3% schema compliance, and 73% token reduction over ReAct agents $73,500 → $19,900 tokens/game) at $0.46 per game. Within this model configuration, these results suggest that phase-bounded architectural structure correlates more strongly with alignment quality than prompting strategy alone.
Our demonstration lets attendees generate Bloom's-aligned games from natural language in under 60 seconds, inspect Quality Gate outputs at each pipeline phase, and browse a curated library of 50 games spanning all 15 mechanic types.

GAMED.AI: A Hierarchical Multi-Agent Framework for Automated Educational Game Generation

This paper introduces a new multi-agent framework, CMTD (Cognitive Modeling with Traits and Distortions), for multimodal emotion recognition in conversations (MERC). Instead of relying on shallow analysis of emotions, CMTD reconstructs a cognitive model by taking advantage of stable personality traits, dynamic cognitive distortions, visual and acoustic features of interlocutors to enhance the emotional intelligence of LLMs. CMTD includes trait, distortion detection, vision, and speech agents that provide psychological and multimodal indicators for the fusion agent to make the final prediction. Experimental results on MELD and IEMOCAP show that traits temper negativity bias from distortions, and cognitive modeling with psychological, visual, and acoustic information can improve the performance of MERC.
CMTD is flexible and easy to adapt to advanced emotional AI systems (Github link: https://github.com/Shaun-le/CMTD.git).

CMTD: Cognitive Modeling with Traits and Distortions for Multimodal Emotion Recognition in Conversations

Culturally aware safeguards are crucial for AI alignment in real-world settings, where safety extends beyond common sense and encompasses diverse local values, norms, and region-specific regulations. However, building large-scale, culturally grounded datasets is challenging due to limited resources and a scarcity of native annotators. Consequently, many safeguard models rely on machine translation of English datasets, often missing regional and cultural nuances. We present a novel agentic data-generation framework to scalably create authentic, region-specific safety datasets for Southeast Asia (SEA). On this foundation, we introduce the SEA-Guard family, the first multilingual safeguard models grounded in SEA cultural contexts. Evaluated across multiple benchmarks and cultural variants, SEA-Guard consistently outperforms existing safeguards at detecting regionally sensitive or harmful content while maintaining strong general safety performance.

SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia

While Large Language Models (LLMs) demonstrate remarkable reasoning, complex optimization tasks remain challenging, requiring domain knowledge and robust implementation. However, existing benchmarks focus narrowly on Mathematical Programming and Combinatorial Optimization, hindering comprehensive evaluation. To address this, we introduce OptiVerse, a comprehensive benchmark of 1,000 curated problems spanning neglected domains, including Stochastic Optimization, Dynamic Optimization, Game Optimization, and Optimal Control, across three difficulty levels: Easy, Medium, and Hard. The experiments with 22 LLMs of different sizes reveal sharp performance degradation on hard problems, where even advanced models like GPT-5.2 and Gemini-3 struggle to exceed 27% accuracy. Through error analysis, we identify that modeling & logic errors remain the primary bottleneck. Consequently, we propose a Dual-View Auditor Agent that improves the accuracy of the LLM modeling process without introducing significant time overhead. OptiVerse will serve as a foundational platform for advancing LLMs in solving complex optimization challenges.

OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving

Safeguard models help large language models (LLMs) detect and block harmful content, but most evaluations remain English-centric and overlook linguistic and cultural diversity. Existing multilingual safety benchmarks often rely on machine-translated English data, which fails to capture nuances in low-resource languages. Southeast Asian (SEA) languages are underrepresented despite the region’s linguistic diversity and unique safety concerns, from culturally sensitive political speech to region-specific misinformation. Addressing these gaps requires benchmarks that are natively authored to reflect local norms and harm scenarios. We introduce SEA-SafeguardBench, the first human-verified safety benchmark for SEA, covering eight languages, 21,640 samples, across three subsets: general, in-the-wild, and content generation. The experimental results from our benchmark demonstrate that even state-of-the-art LLMs and guardrails are challenged by SEA cultural and harm scenarios and underperform when compared to English texts.

SEA-SafeguardBench: Culturally Grounded Safety Benchmark for Southeast Asian Languages

Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thinking approaches often lead to overthinking, where models produce excessively verbose responses even for simple queries, resulting in test-time inefficiency and even degraded accuracy. Prior work has attempted to mitigate this issue via adaptive reasoning strategies, but these methods largely overlook a fundamental bottleneck: visual perception failures. We argue that stable reasoning critically depends on low-level visual grounding, and that reasoning errors often originate from imperfect perception rather than insufficient deliberation. To address this limitation, we propose Gated Perception-Reasoning Optimization (GPRO), a meta-reasoning controller that dynamically routes computation among three decision paths at each generation step: a lightweight fast path, a slow perception path for re-examining visual inputs, and a slow reasoning path for internal self-reflection. To learn this distinction, we derive large-scale failure attribution supervision from approximately 790k samples, using teacher models to distinguish perceptual hallucinations from reasoning errors. We then train the controller with multi-objective reinforcement learning to optimize the trade-off between task accuracy and computational cost under uncertainty. Experiments on five benchmarks demonstrate that GPRO substantially improves both accuracy and efficiency, outperforming recent slow-thinking methods while generating significantly shorter responses.

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization

Vision--language models (VLMs) can achieve high accuracy while still accepting **culturally plausible but visually incorrect** interpretations. Existing hallucination benchmarks rarely test this failure mode, particularly outside Western contexts and English. We introduce **M$^2$CQA**, a culturally grounded multimodal benchmark built from images spanning 17 MENA countries, paired with contrastive true and counterfactual statements in English, Arabic, and its dialects. To isolate hallucination beyond raw accuracy, we propose the **CounterFactual Hallucination Rate (CFHR)**, which measures counterfactual acceptance conditioned on correctly answering the true statement. Evaluating state-of-the-art VLMs under multiple prompting strategies, we find that CFHR rises sharply in Arabic, especially in dialects, even when true-statement accuracy remains high.
Moreover, reasoning-first prompting consistently increases counterfactual hallucination, while answering before justifying improves robustness. We make the dataset publicly available for the community (https://huggingface.co/datasets/QCRI/M2CQA)).

Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models

Predicting earnings surprises through the analysis of earnings conference call transcripts has attracted increasing attention from the financial research community. Conference calls serve as critical communication channels between company executives, analysts, and shareholders, offering valuable forward-looking information. However, these transcripts present significant analytical challenges, typically containing over 5,000 words with substantial redundancy and industry-specific terminology that creates obstacles for language models. In this work, we propose the Sparse Autoencoder for Financial Representation Enhancement (SAE-FiRE) framework to address these limitations by extracting key information while eliminating redundancy. SAE-FiRE employs Sparse Autoencoders (SAEs) to efficiently identify patterns and filter out noises, and focusing specifically on capturing nuanced financial signals that have predictive power for earnings surprises. Experimental results indicate that the proposed method can significantly outperform comparing baselines.

SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection

Reasoning language models are controlled through explicit modes such as Think and No-think, yet we find that these behaviors are largely governed by a few token-level triggers rather than high-level instructions. Through attention analysis and controlled prompting experiments, we show that a leading ``Okay'' token induces reasoning behavior, while the newline pattern following `</think>` suppresses it. Based on this observation, we propose Mid-Think, a simple training-free prompting format that combines these triggers to achieve intermediate-budget reasoning, consistently outperforming fixed-token and prompt-based baselines in terms of the accuracy--length trade-off. Furthermore, applying Mid-Think to RL training after SFT reduces training time by approximately 15% while improving final performance of Qwen3-8B on AIME from 69.8% to 72.4% and on GPQA from 58.5% to 61.1%, demonstrating its effectiveness for both inference-time control and RL-based reasoning training.

Downloads

Next from ACL 2026

AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse

Similar lecture

Is C4 Dataset Enough for Pruning? An Investigation of Calibration Data for LLM Pruning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES