United States

Large Language Models (LLMs) have demonstrated remarkable capabilities in machine translation. However, maintaining discourse coherence and terminological consistency remains a persistent challenge in document-level translation (DocMT). Existing solutions, such as memory-based agents, predominantly rely on explicit context concatenation. This paradigm treats historical context as a static external resource, which often leads to context dilution, high inference latency, and superficial knowledge integration. To address these limitations, we propose AdaDPI, an adaptive agentic framework that shifts the DocMT paradigm from static retrieval to dynamic parametric internalization. Specifically, we design a linguistic uncertainty monitor (LUM) to actively detect critical discourse discontinuities by the model&#39;s epistemic uncertainty. Upon detection, a context-to-parameter integrator (CPI) compiles retrieved external constraints directly into the model&#39;s intrinsic state via an online parameter adaptation mechanism. Through the online parameter adaptation on a lightweight adapter, AdaDPI internalizes document-specific norms into the model&#39;s intrinsic representations, enabling a progressive evolution of the translation strategy as the discourse unfolds. Extensive experiments on the discourse-rich GuoFeng and IWSLT2017 datasets demonstrate that AdaDPI significantly outperforms the SoTA baselines by more than 5 points on the consistency metric.

ACL 2026

AdaDPI: Document-level Translation Adaptive Agent via Dynamic Parametric Internalization

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

Large Language Models (LLMs) have demonstrated remarkable capabilities in machine translation. However, maintaining discourse coherence and terminological consistency remains a persistent challenge in document-level translation (DocMT). Existing solutions, such as memory-based agents, predominantly rely on explicit context concatenation. This paradigm treats historical context as a static external resource, which often leads to context dilution, high inference latency, and superficial knowledge integration. To address these limitations, we propose AdaDPI, an adaptive agentic framework that shifts the DocMT paradigm from static retrieval to dynamic parametric internalization. Specifically, we design a linguistic uncertainty monitor (LUM) to actively detect critical discourse discontinuities by the model's epistemic uncertainty. Upon detection, a context-to-parameter integrator (CPI) compiles retrieved external constraints directly into the model's intrinsic state via an online parameter adaptation mechanism. Through the online parameter adaptation on a lightweight adapter, AdaDPI internalizes document-specific norms into the model's intrinsic representations, enabling a progressive evolution of the translation strategy as the discourse unfolds. Extensive experiments on the discourse-rich GuoFeng and IWSLT2017 datasets demonstrate that AdaDPI significantly outperforms the SoTA baselines by more than 5 points on the consistency metric.

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.

Vision–Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model stealing or adversarial fine-tuning, while transferable attacks from natural images introduce visible distortions that clinicians can easily detect. To address this, we propose MedFocusLeak, a highly transferable black-box multimodal attack that induces incorrect yet clinically plausible diagnoses while keeping perturbations imperceptible. The method injects coordinated perturbations into non-diagnostic background regions and employs an attention-distraction mechanism to shift the model’s focus away from pathological areas. Extensive evaluations across six medical imaging modalities show that MedFocusLeak achieves state-of-the-art performance, generating misleading yet realistic diagnostic outputs across diverse VLMs. We further introduce a unified evaluation framework with novel metrics that jointly capture attack success and image fidelity, revealing a critical weakness in the reasoning capabilities of modern clinical VLMs.

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

WebAgents have demonstrated strong capabilities in autonomously completing complex web tasks, yet their computational efficiency vulnerabilities have received limited attention. Adversaries can inject malicious prompts into web pages, causing WebAgents to generate unnecessarily long reasoning processes and incur excessive computational cost, termed Computational Cost Attacks (CCA). In this paper, to systematically study this vulnerability under realistic black-box settings, we propose CostBomb, a generation-then-selection attack framework that leverages large language models to generate diverse adversarial prompts and a reinforcement learning–enhanced selector to identify the most effective perturbations. Extensive experiments on multiple real-world web benchmarks reveal that existing WebAgents are highly vulnerable to CCA, suffering substantial increases in computational cost without compromising successful task completion. Our findings highlight an overlooked dimension of WebAgent robustness and underscore the urgent need for efficiency-aware defenses.

When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents

Psychiatric interviewing is a strategic, goal-oriented interaction that requires proactively steering the conversation to elicit latent information. However, existing methods often degenerate into rigid interrogation or aimless chitchat due to a lack of strategic planning. In this work, we introduce S4, a comprehensive framework grounded in Speech Act Theory, modeling the interview as a unified process of internal strategy (Illocution and Perlocution) and external realization (Locution). We synthesize a large-scale dataset with fine-grained psychiatric speech act annotations. Trained on this data, S4Dial employs reinforcement learning driven by long-term therapeutic effects to optimize the strategic chaining of atomic acts, aiming to maximally elicit information and maintain patient engagement. Experiments demonstrate that S4 significantly outperforms baselines, validating the effectiveness of our effect-driven strategic modeling.

S^4: Operationalizing Speech Act Theory for Strategic Semi-Structured Psychiatric Interview

Quantization has shown strong results in preserving model quality under compression. However, under aggressive bit-width reductions, even quantization may require additional information to prevent performance degradation. A natural source of it is second-order curvature information, captured by the Hessian. Since the Hessian of the model layers is prohibitively large, direct computation is infeasible, making structured parameterizations and approximations crucial in practice.

In this work, we propose efficient Kronecker-factored approximation yielding state-of-the-art performance when integrated into existing quantization schemes. Evaluations on the LLaMA and Qwen model families show near-baseline quality at 4-bit compression and only a 5–6% degradation at 2-bit. Moreover, our method substantially accelerates the most expensive component in second-order quantization -- Hessian parameterization -- achieving up to a 10× speedup over prior approaches.

Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization

Hallucination remains a critical bottleneck for large language models (LLMs), undermining their reliability in real-world applications, especially in Retrieval-Augmented Generation (RAG) systems. While existing hallucination detection methods employ LLM-as-a-judge to verify LLM outputs against retrieved evidence, they suffer from inherent *confirmation bias*, where the verifier inadvertently reproduces the errors of the original generation. To address this, we introduce **M**ulti-**A**gent **R**einforced self-**C**heck for **H**allucination (MARCH), a framework that enforces rigorous factual alignment by leveraging deliberate *information asymmetry*. MARCH orchestrates a collaborative pipeline of three specialized agents: a Solver, a Proposer, and a Checker. The Solver generates an initial RAG response, which the Proposer decomposes into claim-level verifiable atomic propositions. Crucially, the Checker validates these propositions against retrieved evidence in isolation, deprived of the Solver's original output. This well-crafted information asymmetry scheme breaks the cycle of self-confirmation bias. By training this pipeline with multi-agent reinforcement learning (MARL), we enable the agents to co-evolve and optimize factual adherence. Extensive experiments across hallucination benchmarks demonstrate that MARCH substantially reduces hallucination rates. Notably, an 8B-parameter LLM equipped with MARCH achieves performance competitive with powerful closed-source models. MARCH paves a scalable path for factual self-improvement of LLMs through co-evolution. The code is at https://github.com/Qwen-Applications/MARCH.

MARCH: Multi-Agent Reinforced Check for Hallucination

Guard models are widely used to detect harmful content in user prompts and LLM responses. However, state-of-the-art guard models rely solely on terminal-layer representations and overlook the rich safety-relevant features distributed across internal layers. We present SIREN, a lightweight guard model that harnesses these internal features. By identifying safety neurons via linear probing and combining them through an adaptive layer-weighted strategy, SIREN builds a harmfulness detector from LLM internals without modifying the underlying model. Our comprehensive evaluation shows that SIREN substantially outperforms state-of-the-art open-source guard models across multiple benchmarks while using $250\times$ fewer trainable parameters. Moreover, SIREN exhibits superior generalization to unseen benchmarks, naturally enables real-time streaming detection, and significantly improves inference efficiency compared to generative guard models. Overall, our results highlight LLM internal states as a promising foundation for practical, high-performance harmfulness detection.

LLM Safety From Within: Detecting Harmful Content with Internal Representations

With the rapidly improving reasoning abilities of Large Language Models (LLMs), there is also a rising demand to use them in a wide variety of domains. This brings about the need to carefully evaluate the limits of the capabilities of these models with various tests and benchmarks. Graph structures are ubiquitous in real-world data, and are often used to represent and analyze relationship patterns within data. Many benchmarks have already been proposed in the graph literature to test the reasoning ability of LLMs to follow and execute graph algorithms. However, due to the limited context length of LLMs, these benchmarks consist of very small graphs. In real-world data, the size of graphs can be significantly larger, and in many cases, not fully accessible. In this paper, we examine a class of problems that arises with very large graphs having limited accessibility. We propose a large graph benchmark dataset, EstGraph, and introduce four distinct tasks designed to estimate large graph properties. We evaluate the reasoning abilities of LLMs on these tasks using a wide variety of graph datasets. In addition, we provide task-specific prompt constructions based on random walk sampling of large graphs (up to millions of nodes) that effectively convey sufficient information to LLMs within the limits of context length.

Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks

Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Current routing methods primarily rely on direct mapping from queries to models based on surface-level features, making them susceptible to the memorization trap and leading to poor generalizability on out-of-distribution (OOD) data. In this paper, we propose DecoR, a novel routing framework that recasts the routing task as a matching process of sifting similar queries from historical logs, effectively mitigating the memorization trap. To enhance matching accuracy, we introduce a query capability deconstruction method that decouples linguistic surface forms from task-intrinsic requirements, directing matching toward capability dimensions to ground decisions in essential task attributes. Furthermore, we develop CodaSet, a comprehensive benchmark for assessing routing generalization, where experimental results demonstrate that DecoR maintains superior accuracy while substantially lowering inference costs across both in-distribution and OOD settings.

Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching

True general intelligence requires not only a model of the physical world but also a social world model: the capacity to infer how individual mental states interact and crystallize into group-level outcomes. Despite notable progress in individual-level Theory of Mind (ToM) reasoning, existing multimodal large language models systematically fail at this: collective behavior emerges non-linearly from social tensions, conformity dynamics, and structural constraints, and cannot be recovered by summing individual intentions. We present ***GroupToM-Bench***, the first multimodal benchmark for group-level ToM, built around a causal chain spanning micro-level BDI states (belief, desire, intention), meso-level group tension and structural constraints, and macro-level outcome prediction and mechanistic attribution. To probe this full arc, we develop a seven-level cognitive audit framework. Experiments reveal that frontier models perform significantly below human levels, exposing fundamental blind spots in modeling social structures and nonlinear collective behavior.

GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs

We investigate belief-like representations in decoder-only autoregressive LLMs using linear controlled probes on residual stream activations and single attention heads. Following Herrmann and Levinstein’s (2025) criteria (Accuracy, Use, Coherence, and Uniformity) we find that large models exhibit strong truth sensitivity (Accuracy), and steering activations along probe directions reliably changes downstream behavior (Use). Coherence, measured via calibrated probes and cross-dataset probing, is moderate across models, while training on diverse data yields domain-consistent truth directions (Uniformity). The results are particularly encouraging at the head level and align with some standard philosophical accounts of belief, e.g., minimal functionalism, supporting the view that LLMs can maintain propositional attitudes under such theoretical frameworks.

Downloads

Next from ACL 2026

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

Similar lecture

Exploring Discourse Structure in Document-level Machine Translation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES