United States

Post-training compression of Multimodal LLMs faces a fundamental geometric conflict: parameter subspaces optimized for text often suppress orthogonal visual features. We demonstrate that standard SVD fails to resolve this cross-modal mismatch, causing catastrophic visual degradation. To bridge this gap, we introduce Joint-Whitening SVD (JW-SVD), a dual-objective framework that aligns vision and language manifolds via a Joint Covariance basis, preserving features critical to both. Additionally, we propose Global Spectrum-Aware Truncation to dynamically transfer parameter budget from the redundant Vision Tower to the sensitive Backbone. Experiments on Qwen2.5-VL and Llama-3-Next confirm that JW-SVD demonstrates superior retention of both text and image capabilities. In addition, it resolves the modality trade-off: it recovers over 30% of perceptual performance lost by baselines while maintaining parity in textual reasoning, enabling robust multimodal performance even at extreme compression rates.

ACL 2026

JW-SVD: Bridging the Cross-Modal Mismatch in Post-Training MLLM Compression

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022! I believe this conference has been complicated beyond any precedent. Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm. We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community. Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well: we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)

To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

EMNLP 2022

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

poster

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.

This paper presents AutoRAN, the first framework to automate the hijacking of internal safety reasoning in large reasoning models (LRMs). At its core, AutoRAN pioneers an execution simulation paradigm that leverages a weaker but less-aligned model to simulate execution reasoning for initial hijacking attempts and iteratively refine attacks by exploiting reasoning patterns leaked through the target LRM's refusals. This approach steers the target model to bypass its own safety guardrails and elaborate on harmful instructions. We evaluate AutoRAN against state-of-the-art LRMs, including GPT-o3/o4-mini and Gemini-2.5-Flash, across multiple benchmarks (AdvBench, HarmBench, and StrongReject). Results show that AutoRAN achieves approaching 100% success rate within one or few turns, effectively neutralizing reasoning-based defenses even when evaluated by robustly aligned external models. This work reveals that the transparency of the reasoning process itself creates a critical and exploitable attack surface, highlighting the urgent need for new defenses that protect models' reasoning traces rather than merely their final outputs.

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models

Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a critical bottleneck, often prohibiting efficient training on limited hardware. While existing KV compression techniques offer a remedy for inference, directly applying them to RL training induces a severe policy mismatch, leading to catastrophic performance collapse. To address this, we introduce Sparse-RL, which empowers stable RL training under sparse rollouts. We show that instability arises from a fundamental policy mismatch among the dense old policy, the sparse sampler policy, and the learner policy. To mitigate this issue, Sparse-RL incorporates Sparsity-Aware Rejection Sampling and Importance-based Reweighting to correct the off-policy bias introduced by compression-induced information loss. Experimental results show that Sparse-RL reduces rollout overhead compared to dense baselines while preserving the performance. Furthermore, Sparse-RL inherently implements sparsity-aware training, significantly enhancing model robustness during sparse inference deployment.

 Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts

Multi-party social dialogue remains underexplored in the literature,
in part due to the difficulty and cost of evaluation. As a result,
recent work on synthetic dialogue generation often relies on automated
metrics and LLM-as-a-Judge frameworks, despite limited evidence that
such judges reflect human preferences in social settings. In this work,
we introduce a lightweight and controllable multi-party dialogue
generation framework (\textsc{MPOD}) as an experimental instrument for
studying generation and evaluation in social interaction. Using this
framework, we conduct human evaluations of open-domain multi-party
dialogue simulation and directly compare human judgments against
state-of-the-art LLM judges. Across 319 pairwise comparisons, we
observe near-random agreement between humans and automated judges
(Cohen's $\kappa \approx 0.11$), driven by systematic behaviors
including extreme tie aversion and strong sensitivity to
assistant-style verbosity. Crucially, human–human inter-annotator
agreement ($\kappa = 0.29$) is substantially higher than human–LLM
agreement. To isolate the
mechanism underlying this misalignment, we introduce a controlled
\textit{Transplant Ablation}, showing that LLM judges consistently
prefer conversations containing a single proprietary, assistant-style
agent. Additional stress tests show that judges prefer GPT-style
conversations even when utterance order is randomly shuffled,
indicating insensitivity to conversational structure and coherence.
Our findings provide controlled evidence that current
instruction-tuned LLM judges do not reliably reflect human preferences for naturalness, engagingness, and overall quality in multi-party social dialogue, calling into question their widespread
use for validating synthetic conversational data.

 Simple Agents, Biased Judges: Efficient Multi-Party Dialogue Generation & The Evaluation Gap

Despite the growing use of large language models (LLMs) for writing tasks, users may hesitate to rely on LLMs when personal style is important. Post-editing LLM-generated drafts or translations is a common collaborative writing strategy, but it remains unclear whether users can effectively reshape LLM-generated text to reflect their personal style. We conduct a pre-registered online study ($n=81$) in which participants post-edit LLM-generated drafts for writing tasks where personal style matters to them. Using embedding-based style similarity metrics, we find that post-editing increases stylistic similarity to participants' unassisted writing and reduces similarity to fully LLM-generated output. However, post-edited text still remains stylistically closer in style to LLM text than to participants' unassisted control text, and it exhibits reduced stylistic diversity compared to unassisted human text. We find a gap between perceived stylistic authenticity and model-measured stylistic similarity, with post-edited text often perceived as representative of participants' personal style despite remaining detectable LLM stylistic traces.

Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style

Automated interaction with graphical user interfaces (GUIs) is central to General Artificial Intelligence yet remains challenging within Super App ecosystems, characterized by non-standard rendering and absent accessibility metadata. While GUI agents often rely on explicit accessibility trees or static imitation, they are less explored for dynamic environments marked by sparse feedback and implicit visual cues. 
We present GUI0, a framework synergizing autonomous data synthesis with dual-agent co-evolution. GUI0 establishes a domain-aware foundation model via synthesized corpora and employs curriculum-driven reinforcement learning, where a curriculum agent generates boundary tasks to optimize an actor agent.
Empirical results demonstrate three key advantages: (1) State-of-the-art performance on the SuperAPP benchmark, outperforming Gemini-2.5-Pro and Claude-4-Sonnet; (2) universal efficacy across diverse base models, consistently yielding substantial improvements on both Qwen2.5-VL and GUI-Owl variants; and (3) robust zero-shot generalization to standard GUIs (e.g., +62.7\% on ScreenSpot Pro).

GUI0: Self-Evolving Foundational GUI Agents in Super App Ecosystems

Sparse Mixture of Experts (SMoE) architectures reduce computational cost by activating only a subset of experts per token, yet they often retain large memory footprints and exhibit significant redundancy, both within and across layers. We propose GMoE, a sparse MoE architecture designed to explicitly address these inefficiencies. Instead of maintaining separate expert sets for each layer, GMoE uses Global Experts shared across all layers and adds a Local Expert per layer for layer-specific adaptation. This architecture reuses Global Experts across layers, thereby mitigating inter-layer redundancy while substantially reducing model parameters. In addition, we introduce a Global Router with a GRU-based recurrent component shared across layers and layer-specific routing heads that propagate routing logits across layers. This routing mechanism couples routing decisions across layers, progressively refines routing paths, and helps mitigate intra-layer redundancy. Across diverse language modeling corpora and downstream benchmarks, GMoE remains competitive while using substantially fewer parameters. Routing path analyses and an ablation study show that GMoE reduces cross-layer routing concentration and increases path diversity, with the Global Experts, the Local Expert, and the Global Router all contributing to the gains. The code is available at https://github.com/GEONWOOHONG/GMoE.

GMoE: Global Mixture of Experts with Logit Propagation

Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools during reasoning. Existing TIR methods typically rely on external tool documentation during reasoning. However, this leads to tool mastery difficulty, tool size constraints, and inference inefficiency. To mitigate these issues, we explore Tool-Internalized Reasoning (TInR), aiming at facilitating reasoning with tool knowledge internalized into LLMs. Achieving this goal presents notable requirements, including tool internalization and tool-reasoning coordination. To address them, we propose TInR-U, a tool-internalized reasoning framework for unified reasoning and tool usage. TInR-U is trained through a three-phase pipeline: 1) tool internalization with a bidirectional knowledge alignment strategy; 2) supervised fine-tuning warm-up using high-quality reasoning annotations, and 3) reinforcement learning with TInR-specific rewards. We comprehensively evaluate our method across in-domain and out-of-domain settings. Experiment results show that TInR-U achieves superior performance in both settings, highlighting its effectiveness and efficiency. The codes are attached in the supplementary file for review.

TInR: Exploring Tool-Internalized Reasoning in Large Language Models

Multimodal large language models (MLLMs) are making rapid strides in complex visual reasoning. This survey synthesizes the emerging paradigm of Image-Grounded Chain-of-Thought (IG-CoT), where models ground intermediate inferences by interleaving textual rationales with visual state updates. We formalize IG-CoT, present a method-centric taxonomy covering prompting, supervised fine-tuning, and reinforcement learning, and map these techniques to representative benchmarks. Our analysis identifies two domains where IG-CoT offers significant advantages: detail-oriented reasoning requiring meticulous perception, and imagined-world reasoning for simulating unseen states in games, geometry, and planning. We discuss the practical trade-offs of current methods regarding controllability, data, and compute. We conclude by highlighting key challenges (efficiency, data quality, and generative capabilities) and outlining promising future directions, including lightweight architectures, richer intermediate supervision, and method-aware evaluations that better assess faithfulness and long-horizon reasoning. We maintain a continuously updated paper list at https://github.com/dddraxxx/Awesome-Image-Grounded-CoT.

Revealing the Seen, Imagining the Beyond: A Survey of Image-Grounded Chain-of-Thought Reasoning in Multimodal LLMs

Transformer-based Small (SLMs) and Large Language Models (LLMs) achieve strong effectiveness in text classification (TC), yet deployment requires reliable confidence estimates. Although miscalibration in Transformers has been reported, evidence for TC under fine-tuning remains limited. We evaluate the calibration of fine-tuned SLMs and LLMs against Logistic Regression, a classical, well-calibrated baseline, and find that, despite superior effectiveness, Transformers remain markedly overconfident. Crucially, we show that widely used calibration metrics, such as Expected Calibration Error and Brier Score, become biased in high-effectiveness regimes, where the dominance of correct predictions masks severe miscalibration on errors, sometimes even suggesting better calibration than Logistic Regression, a well-known calibrated method. To address this limitation, we propose the Balanced Brier Score (BBS), which balances the contribution of correct and incorrect predictions within confidence bins. BBS reveals substantially poorer calibration in both SLMs and LLMs, consistent with qualitative evidence from calibration curves. These findings challenge current calibration assessment practices and provide a more reliable alternative for evaluating confidence quality in Transformer-based TC.

 When High Accuracy Hides Poor Calibration: Rethinking Confidence Evaluation in Transformer-Based Text Classification with Balanced Brier Score

Despite the success of large language models (LLMs) on general-purpose tasks, their performance in highly specialized domains such as biomedicine remains unsatisfactory. A key limitation is the inability of LLMs to effectively leverage biomedical tools, which clinical experts and biomedical researchers rely on extensively in daily workflows. While recent general-domain tool-calling datasets have substantially improved the capabilities of LLM agents, existing efforts in the biomedical domain largely rely on in-context learning and restrict models to a small set of tools. 
To address this gap, we introduce BioTool, a comprehensive biomedical tool-calling dataset designed for fine-tuning LLMs. BioTool comprises 34 frequently used tools collected from the NCBI, Ensembl, and UniProt databases, along with 7,040 high-quality, human-verified query–API call pairs spanning variation, genomics, proteomics, evolution, and general biology. Fine-tuning a 4-billion-parameter LLM on BioTool yields substantial improvements in biomedical tool-calling performance, outperforming cutting-edge commercial LLMs such as GPT-5.1. Furthermore, human expert evaluations demonstrate that integrating a BioTool-fine-tuned tool caller significantly improves downstream answer quality compared to the same LLM without tool usage, highlighting the effectiveness of BioTool in enhancing the biomedical capabilities of LLMs. The full dataset and evaluation code are available at https://github.com/gxx27/BioTool.

Downloads

Next from ACL 2026

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models

Similar lecture

Numerical Optimizations for Weighted Low-rank Estimation on Language Models