United States

Red team testing, an effective proactive method for evaluating the security of multimodal large language models (MLLMs), requires an expanding toolkit alongside the development of MLLM safeguards. We propose the Reference Attack, a powerful tool for red team testing against MLLMs. 
The Reference Attack is a reference-guided cross-modal jailbreak method that enhances existing prompt-to-image injection attacks by exploiting MLLMs’ semantic reconstruction capabilities. Our method embeds malicious prompts in non-text modalities (e.g., images, spreadsheets) and constructs recursive symbolic references in text, enabling MLLMs to gradually recover and generate harmful content through layered reference resolution.
The attack introduces a new vector that circumvents conventional content moderation by exploiting MLLMs&#39; lack of security checks during cross-modal reference resolution. We evaluate the Reference Attack on leading MLLMs, including ChatGPT, Gemini, Claude, and the widely used open-source LLaMA model, and achieved an attack success rate of over 93\% across all tested models. Compared to state-of-the-art attacks, Reference Attack achieves higher success rates than all baselines under identical evaluation, with a maximum gain of 70.8\%. Our study reveals a critical gap in MLLM security and highlights the need for strict security auditing of cross-modal interactions in future content moderation.

ACL 2026

Reference Attack: A New Cross-Modal Jailbreaking Attack against Multimodal Large Language Models

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Red team testing, an effective proactive method for evaluating the security of multimodal large language models (MLLMs), requires an expanding toolkit alongside the development of MLLM safeguards. We propose the Reference Attack, a powerful tool for red team testing against MLLMs. 
The Reference Attack is a reference-guided cross-modal jailbreak method that enhances existing prompt-to-image injection attacks by exploiting MLLMs’ semantic reconstruction capabilities. Our method embeds malicious prompts in non-text modalities (e.g., images, spreadsheets) and constructs recursive symbolic references in text, enabling MLLMs to gradually recover and generate harmful content through layered reference resolution.
The attack introduces a new vector that circumvents conventional content moderation by exploiting MLLMs' lack of security checks during cross-modal reference resolution. We evaluate the Reference Attack on leading MLLMs, including ChatGPT, Gemini, Claude, and the widely used open-source LLaMA model, and achieved an attack success rate of over 93\% across all tested models. Compared to state-of-the-art attacks, Reference Attack achieves higher success rates than all baselines under identical evaluation, with a maximum gain of 70.8\%. Our study reveals a critical gap in MLLM security and highlights the need for strict security auditing of cross-modal interactions in future content moderation.

technical paper

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.

**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.

Retrieval-Augmented Generation (RAG) is widely used to ground large language models (LLMs) in external knowledge and improve factual accuracy. Prior work has explored iterative and self-reflective mechanisms to refine reasoning, but these approaches rely on internal model judgment and lack formally grounded, verifiable feedback. As a result, RAG systems may still produce logically inconsistent or contradictory answers in multi-step reasoning. In this paper, we propose LCR-RAG, a framework that integrates neuro-symbolic verification with reinforcement learning to explicitly optimize logical consistency. The core of our approach is a Logic-Consistency-driven Reward (LCR), which converts discrete logical signals—such as contradictions or incomplete inference chains—into a structured reward signal. This reward guides a PPO-based agent to iteratively rewrite queries and correct reasoning errors. Experiments on HotpotQA, ASQA, and TriviaQA show that LCR-RAG consistently outperforms strong RAG baselines, with ablation results indicating that the LCR mechanism is the primary source of improvement, even under noisy or conflicting retrieval conditions.

LCR-RAG: Enhancing Logical Consistency in Retrieval-Augmented Generation via Neuro-symbolic Reinforcement Learning

Large reasoning models (LRMs) achieve strong performance by externalizing explicit reasoning traces before producing the answer, yet suffer from overthinking challenge that allocates uniformly heavy computation to queries of varying difficulty. While proprietary models mitigate this via opaque routing, open-source LRMs still lack an efficient mechanism to internalize adaptive reasoning due to both expensive training cost and limited disclosure of training recipes. In response, we introduce RPO (Root-token Policy Optimization), a framework that enables LRMs to self-determine when to reason by training only the initial root token (e.g., whether to invoke the \<think\> tag) via group relative reward and group-wise advantages. By focusing on this pivotal branching point, RPO drastically reduces training overhead and VRAM usage. Across multiple model families and scales, RPO learns difficulty-aware adaptive thinking at just 
2% of the training compute of prior adaptive-reasoning methods.

Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking

Existing long-document question answering systems typically process texts as flat sequences or use heuristic chunking, which overlook the discourse structures that naturally guide human comprehension. We present a discourse-aware hierarchical framework that leverages rhetorical structure theory (RST) for long document question answering. Our approach converts discourse trees into sentence-level representations and employs LLM-enhanced node representations to bridge structural and semantic information. The framework involves three key innovations: language-universal discourse parsing for lengthy documents, LLM-based enhancement of discourse relation nodes, and structure-guided hierarchical retrieval. Extensive experiments on four datasets demonstrate consistent improvements over existing approaches through the incorporation of discourse structure, across multiple genres and languages. Moreover, the proposed framework exhibits strong robustness across diverse document types and linguistic settings.

Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering

Parameter-efficient fine-tuning (PEFT) must balance effectiveness and efficiency: low-rank methods can be costly, while global representation edits often underfit token-level contexts. We propose **Token-Aware Representation Editing (TARE)**, a PEFT method that performs fine-grained, token-specific edits with a small additional inference overhead and minimal tuning.
After each FFN block in a transformer-like model, we adopt a lightweight selector that scores a small pool of hidden representation editors for each token, activates only the top-k editors, and mixes their element-wise scaling/bias updates. This design achieves superior performance while maintaining computational efficiency, yielding a more favorable Pareto frontier compared to state-of-the-art (SOTA) methods.
Across LLaMA-3-8B (eight knowledge reasoning and seven mathematical reasoning tasks) and RoBERTa-base/large (GLUE), TARE outperforms SOTAs (LoRA, DoRA, MiLoRA, LoReFT, and RED), achieving 86.7% (knowledge reasoning), 76.7% (mathematical reasoning), and 88.3% (GLUE) while tuning only 0.0392% of parameters using about 20 GiB peak GPU memory during training.
An implementation is available at: <https://github.com/PatriciaPulec/tare>.

TARE: Lightweight Token-Aware Representation Editing for Fine-tuning Transformer-like Models

Codec-based language models (LMs) have revolutionized text-to-speech (TTS). However, standard codecs entangle timbre and prosody, which hinders independent control in continuation-based LMs. To tackle this challenge, we propose DisCo-Speech, a zero-shot controllable TTS framework featuring a disentangled speech codec (DisCodec) and an LM-based generator. The core component DisCodec employs a two-stage design: 1) tri-factor disentanglement to separate speech into content, prosody, and timbre subspaces via parallel encoders and hybrid losses; and 2) fusion and reconstruction that merges content and prosody into unified content-prosody tokens suitable for LM prediction, while jointly optimizing reconstruction to address the disentanglement-reconstruction trade-off. This allows the LM to perform prosodic continuation from a style prompt while the decoder injects target timbre, enabling flexible zero-shot control. Experiments demonstrate that DisCo-Speech achieves competitive voice cloning and superior zero-shot prosody control. By resolving the core entanglement at the codec level, DisCo-Speech provides a robust foundation for controllable speech synthesis. Audio samples are available at: https://disco-speech.github.io/DisCo-demo/. Code and weights will be released at: https://github.com/disco-speech/DisCo-Speech upon acceptance.

DisCo_Speech: Controllable Zero-Shot Speech Generation with A Disentangled Speech Codec

Large Language Models (LLMs) often generate factually incorrect content, known as “hallucinations”, which undermine the reliability and safety of their outputs. Existing hallucination detection methods either depend on external knowledge sources, incurring high computational costs and limiting real-time applicability, or extract the model's internal states, leading to poor generalization. To address these issues, this paper proposes ReFL, a hallucination detection framework. ReFL leverages corrective in-context learning to dynamically guide LLMs to recognize their own prediction errors and adjust internal representations, critically without updating model weights. Specifically, by introducing a corrective in-context learning strategy, where triplets of input text, model prediction, and ground-truth label are embedded into the prompt to make the model explicitly aware of its own errors. The model reflects on prior outputs to adjust its internal states and generate semantically structured representations better aligned with factuality. This feedback mechanism encourages the model to shape a more coherent semantic space and enhances the LLM’s internal sensitivity to hallucinations. Experimental results on two benchmark datasets demonstrate that ReFL consistently outperforms existing methods, achieving state-of-the-art performance.

ReFL: Reflective Feedback Learning for Hallucination Detection of Large Language Models

Temporal Knowledge Graph (TKG) extrapolation aims to predict future events based on historical facts. Recent studies have attempted to enhance TKG extrapolation by integrating TKG's evolving structural representations and textual event chains into Large Language Models (LLMs). Yet, two main challenges limit these approaches: (1) The loss of essential spatial-temporal information due to shallow alignment between TKG's graph evolving structural representation and the LLM's semantic space, and (2) the progressive dilution of the TKG's evolving structural features during LLM fine-tuning. To address these challenges, we propose the Spatial-Temporal Knowledge Adapter (STK-Adapter), which flexibly integrates the evolving graph encoder and the LLM to facilitate TKG reasoning. In STK-Adapter, a Spatial-Temporal MoE is designed to capture spatial structures and temporal patterns inherent in TKGs. An Event-Aware MoE is employed to model intricate temporal semantics dependencies within event chains. In addition, a Cross-Modality Alignment MoE is proposed to facilitate deep cross-modality alignment by TKG-guided attention experts. Extensive experiments on benchmark datasets demonstrate that STK-Adapter significantly outperforms state-of-the-art methods and exhibits strong generalization capabilities in cross-dataset task. The code is available at https://github.com/Zhaoshuyuan0246/STK-Adapter.

STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation

While Multimodal Large Language Models (MLLMs) are advancing rapidly, accurately evaluating their capabilities remains challenging. Current paradigms primarily rely on holistic scoring and static leaderboards, which fail to disentangle fine-grained competencies. Specifically, they suffer from “Outcome Bias” by validating only final answers and ignoring intermediate reasoning. To address these limitations, we introduce ATOM (AnaTomy Of MLLM), a novel MLLM-as-a-judge framework designed to shift the focus from ranking to fine-grained diagnosis. ATOM decomposes complex reasoning into atomic criteria anchored in visual elements, enforcing verification against explicit visual facts. Validated on a newly constructed benchmark with rigorous human rankings, ATOM achieves state-of-the-art accuracy, surpassing the strongest baseline by up to 7.92%. Moving beyond ranking, ATOM bridges the gap between assessment and alignment: by pinpointing atomic-level failures, it establishes a closed-loop mechanism for targeted self-correction. This approach enables models to identify and rectify errors autonomously, successfully resolving up to 39.95% of previously failed queries without human intervention.

Beyond Ranking: Fine-Grained Diagnostics and Self-Improvement for MLLMs

Graphical User Interface (GUI) grounding requires mapping natural language instructions to precise pixel coordinates. However, due to visually homogeneous elements and dense layouts, models typically grasp semantic intent yet fail to achieve precise localization. While scaling sampling attempts (Pass@k) reveals potential gains, static self-consistency strategies derived from geometric clustering often yield limited improvements, as the model's predictions tend to be spatially dispersed. In this paper, we propose replacing static consistency strategies with a learnable selection mechanism that selects the optimal target by critiquing its own proposals rendered on the screenshot. Given the significant disparity between the model's grounding and critiquing capabilities, we propose a co-evolving Propose-and-Critic framework. To jointly optimize these, we introduce a maturity-aware adaptive co-evolutionary reinforcement learning paradigm. This approach dynamically balances the training objectives of proposer and critic, where the diversity of the proposer's outputs enhances critic robustness, while the critic's maturing discrimination capability conversely unlocks the proposer's potential for extensive spatial exploration, fostering the mutual reinforcement and co-evolution of both capabilities, thereby ensuring generalizability to adapt to diverse and complex interface layouts. Extensive experiments over 6 benchmarks show that our method significantly enhances both capabilities.

Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding

High-Level Synthesis (HLS) improves IC development productivity by enabling hardware design from C-like languages. However, strict coding constraints and design-specific optimizations limit its widespread adoption. While recent efforts employ large language models (LLMs) to assist HLS design, they often struggle with synthesizability rules and directive semantics. To this end, we introduce ChatHLS, a multi-agent HLS design framework that leverages specialized LLMs for automated debugging and directive tuning. ChatHLS incorporates an adaptive error case expansion mechanism, combined with a reasoning-to-instruction analysis method to accurately diagnose HLS errors. To optimize hardware performance, it enables QoR-aware reasoning to learn the impact of HLS directives on the quality of results (QoR). Experimental results demonstrate that ChatHLS outperforms Gemini-3-pro with a 32.6% relative improvement in debugging, while achieving significant speedups across various HLS kernels and neural network accelerators. These results underscore the potential of ChatHLS for agile hardware development.

Downloads

Next from ACL 2026

LCR-RAG: Enhancing Logical Consistency in Retrieval-Augmented Generation via Neuro-symbolic Reinforcement Learning

Similar lecture

FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES