United States

Retrieval-augmented generation (RAG) effectively enhances the accuracy and timeliness of large language models (LLMs) by incorporating external knowledge retrieved from external sources. However, with the increasing prevalence of LLM-generated content, external corpora used by RAG systems may become contaminated with LLM-generated texts. Such contamination compromises the reliability and quality of retrieved results, ultimately leading to a degradation in RAG performance, and raises concerns about the diminishing presence of human texts and the ``Spiral of Silence&#39;&#39; effect. A natural solution is to incorporate LLM text detectors into the RAG pipeline to filter out LLM-generated texts from the retrieved results. However, their effective use in RAG remains under-explored. In this paper, we explore the usage paradigms of LLM text detectors for RAG and highlight key limitations of off-the-shelf or directly fine-tuned detectors. To this end, we propose a RAG-aware data augmentation strategy that aligns detector training with realistic contamination patterns. Our approach synthesizes training data from both LLM and human texts under diverse generation modes. Experiments show that our method mitigates performance degradation and improves the long-term stability of RAG systems.

ACL 2026

LLM-Generated Text May Harm Your Retrieval! A Robust Detection Strategy for Retrieval-Augmented Generation

## 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.

Retrieval-augmented generation (RAG) effectively enhances the accuracy and timeliness of large language models (LLMs) by incorporating external knowledge retrieved from external sources. However, with the increasing prevalence of LLM-generated content, external corpora used by RAG systems may become contaminated with LLM-generated texts. Such contamination compromises the reliability and quality of retrieved results, ultimately leading to a degradation in RAG performance, and raises concerns about the diminishing presence of human texts and the ``Spiral of Silence'' effect. A natural solution is to incorporate LLM text detectors into the RAG pipeline to filter out LLM-generated texts from the retrieved results. However, their effective use in RAG remains under-explored. In this paper, we explore the usage paradigms of LLM text detectors for RAG and highlight key limitations of off-the-shelf or directly fine-tuned detectors. To this end, we propose a RAG-aware data augmentation strategy that aligns detector training with realistic contamination patterns. Our approach synthesizes training data from both LLM and human texts under diverse generation modes. Experiments show that our method mitigates performance degradation and improves the long-term stability of RAG systems.

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.

Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly in their mathemat- ical reasoning performance. However, GRPO and related entropy regularization methods still struggle with token-level sparse-rewards, which is an inherent challenge in chain-of-thought (CoT) reasoning. These approaches often rely on undifferentiated token-level entropy regu- larization, which easily leads to entropy collapse or model degradation under sparse token rewards. In this work, we propose TEPO, a novel token-level framework that (1) leverages sequence-level likelihood to link group-level rewards with individual tokens via token-level aggregation, and (2) introduces a token-level KL-Divergence mask constraint that targets tokens with positive advantages and decreasing entropy to mitigate abrupt policy updates. Experiments demonstrate that TEPO not only achieves state-of-the-art performance on mathematical reasoning benchmarks but also markedly enhances training stability, reducing convergence time by 50% compared with GRPO/DAPO.

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood

Contrastively trained vision-language models like CLIP, have made remarkable progress in learning joint image-text representations, but still face challenges in compositional understanding. They often exhibit a ``bag-of-words'' behavior—struggling to capture the object relations, attribute-object bindings, and word order dependencies. This limitation arises not only from the reliance on global, single-vector representations for optimization, but also from the insufficient exploitation and modeling of the rich compositional information inherently present in paired image text data. In this work, we propose **MACCO** (**MA**sked **C**ompositional **C**oncept M**O**deling), a framework that masks compositional concepts in one modality and reconstructs them conditioned on the full contextual information from the other, enabling the model to capture and align cross-modal compositional structures more effectively. To facilitate this process, we introduce two auxiliary objectives that jointly align and regularize masked features both inter-modally and intra-modally. Extensive experiments on five compositional benchmarks, along with in-depth analyses, demonstrate that our approach not only significantly enhances compositionality in VLMs but also improves their ability to capture syntactic structure and linguistic information. Additionally, the improved compositionality also benefits text-to-image generation and multimodal large language model.

Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality

LLM-based agents are rapidly being deployed in real-world applications (e.g., digital assistants and customer service), making safety a critical concern. However, in multi-turn, tool-augmented settings, dynamic user interactions, external tool use, and unintended harmful behaviors make robust safety assurance challenging. To address these challenges, we propose **SafeAgent**, a framework that improves agent safety through fully automated synthetic data generation. SafeAgent introduces (1) an open and extensible threat model OTS that decomposes agent risk into instruction-, context-, and action-induced sources to ground safety analysis and alignment; and (2) an automated pipeline that instantiates OTS to surface scenario-specific failure modes, stress-test agents, and generate self-reflective safe responses—without hazardous real-world data collection. We evaluate SafeAgent on two safety benchmarks and one real-world terminal task. Across four widely used open-source models, SafeAgent improves safety performance by 45% on average and delivers a 28.91% gain on the real-world task, outperforming state-of-the-art closed-source models. These results highlight the practical advancement and scalability of SafeAgent in building safer LLM agents for real-world deployment.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator

As human-agent interaction (HAI) evolves toward long-term social companionship, users expect *Original Character (OC)* agents to maintain a consistent persona, manage shared memories, and adapt to ever-changing preferences. However, LLM-based agents optimized by prompting or SFT exhibit a generalization gap: they behave as myopic instruction followers, leading to cascading errors in multi-turn interactions. For the agents to learn trajectory-level value functions that enable farsighted decision-making, we propose the NSARL framework, which formalizes OC companion agents' interactions as a POMDP and decomposes the agent into three sub-policies (Router, Memory, and Persona), optimized via closed-loop RL from AI feedback (RLAIF) with verifiable rewards in a graph-constrained action space. Our preliminary experiments indicate a trade-off: SFT yields stronger persona generation, while NSARL improves structural logic, through conservative strategies (e.g., over-routing) that increase workflow completeness, advocating for a hybrid deployment strategy.

Neuro-Symbolic Agentic Reinforcement Learning for Long-Term Original Character Companionship and Interaction

Human evaluation of machine translation is in an arms race with translation model quality: as our models get better, our evaluation methods need to be improved to ensure that quality gains are not lost in evaluation noise. To improve annotation quality, we experiment with a two-stage version of the current state-of-the-art translation evaluation paradigm (MQM), which we call MQM re-annotation. In this setup, an annotator reviews and edits a set of prior MQM annotations that may have come from themselves, another human annotator, or an automatic system. We demonstrate that rater behavior in re-annotation aligns with our goals, and that re-annotation results in higher-quality annotations, mostly due to finding errors that were missed during the first pass.

MQM Re-Annotation: A Technique for Collaborative Evaluation of Machine Translation

Multilingual language models (LMs) organize representations for typologically and orthographically diverse languages into a shared parameter space, yet the nature of this internal organization remains elusive. In this work, we investigate which linguistic properties — abstract language identity or surface-form cues — shape multilingual representations. To do so, we analyze language-associated units across different model families and scales using the Language Activation Probability Entropy (LAPE) metric, and further decompose activations with Sparse Autoencoders. We find that these units are strongly conditioned on orthography: romanization induces near-disjoint representations that align with neither native-script inputs nor English, while word-order shuffling has limited effect on unit identity. Probing shows that typological structure becomes increasingly accessible in deeper layers, while causal interventions indicate that generation is most sensitive to units that are invariant to surface-form perturbations rather than to units identified by typological alignment alone. Overall, our results suggest that multilingual LMs organize representations around surface form, with linguistic abstraction emerging gradually without collapsing into a unified interlingua.

Multilingual Language Models Encode Script Over Linguistic Structure

Latent reasoning enables Large Language Models (LLMs) to perform multi-step inference within continuous hidden states, offering efficiency gains over explicit Chain-of-Thought (CoT). However, the opacity of these continuous thought vectors hinders their reliability and controllability. This paper bridges the gap between mechanistic interpretability and actionable control. We first present a systematic analysis using structural, causal, and geometric probes, revealing that latent vectors encode compressed, faithful representations of reasoning steps, with early vectors acting as critical causal hubs. Building on this, we operationalize these interpretability insights into a suite of training-free, decode-time interventions that refine the latent reasoning process by imposing the identified geometric and semantic priors. Extensive experiments across multiple model scales and diverse task domains demonstrate that our approaches consistently improve reasoning accuracy. Our interpretability-guided interventions consistently unlock latent capabilities and improve reasoning accuracy without any parameter updates.

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention

Detecting deceptive behavior in LLMs is typically done post-hoc on outputs or by probing static activations. We instead treat deception as a dynamic process, a trajectory through the model's hidden-state space during inference. We capture layerwise activations at sparse "decision points" where the model is uncertain between competing tokens, forming activation trajectories for matched truthful vs. deceptive responses across strategic deception, sycophancy, instructed deception, and confabulation. Across GPT-2 and Llama variants, deceptive generation is associated with changes in trajectory geometry, but increases in path length are model and deception-type-dependent. Sycophancy shows the clearest signal, whereas instructed deception yields near-null signatures. With just 7 geometric features, a lightweight classifier achieves performance comparable to PCA-reduced probing at matched dimensionality for binary sycophancy detection and shows preliminary utility for 4-way deception-type classification. These findings indicate that trajectory-based monitoring can provide process-level signals associated with deceptive generation during inference, complementing methods that focus on endpoint activation states.

Trajectory Signatures of Deception in Large Language Models

Large Language Models based Table Question Answering (LLMs-based TableQA) models excel in NLP field, however, they occasionally exhibit an unfaithful behavior where correct answers are derived through erroneous reasoning paths. In this condition, we propose TrustTable, a neuro-symbolic framework designed to ensure reasoning faithfulness by auditing the reasoning processes of LLMs. Unlike monolithic LLM-based auditors, TrustTable decouples the auditing operation into two orthogonal dimensions. It enforces factual grounding by executing neurally generated Pandas code against the table, and ensures logical soundness by verifying reasoning chains through a LLM-synthesized formal solver. By integrating these symbolic checks, TrustTable enables a Label-Free Audit Loop that systematically identifies and rectifies reasoning flaws without human supervision. In addition, we present the TrustTable-Bench, a diagnostic dataset containing diverse error categories that range from calculation discrepancies to schema misalignments. This benchmark allows for a rigorous quantification of reasoning limitations. Experiments demonstrate that our symbolic audit detects reasoning flaws more accurately than advanced baselines. More broadly, the TrustTable outperforms LLM judges in both majority voting with logical weighting and rejection sampling with process supervision.

TrustTable: A Neuro-Symbolic Auditing Framework for Faithful Table QA

3D Visual Grounding (3DVG) locates objects in 3D scenes based on natural language descriptions. However, existing methods are primarily confined to small-scale indoor data or rely on heavy supervision, failing to generalize to the complexity of large-scale urban environments. To address this limitation, we present CityVG, the first city-scale zero-shot 3D visual grounding framework capable of localizing urban objects without manual annotations. Our approach adopts a retrieval-and-reasoning paradigm comprising two key components. Specifically, we propose a contrastive fine-tuning strategy to align textual queries with urban scene graphs. By leveraging an LLM-driven graph clustering mechanism, we automatically construct high-quality positive and negative training pairs and fine-tune the text encoder via contrastive learning, resulting in a scene-adaptive text encoder that enables efficient alignment without grounding supervision. Complementing this, we introduce a multi-trajectory reward-based Chain-of-Thought (CoT) reasoning strategy for inference. This mechanism iteratively evaluates candidate objects by aggregating reward scores across diverse reasoning trajectories, selecting the target that is most consistent with both appearance and spatial constraints. Extensive experiments on city-scale 3D grounding benchmarks demonstrate that CityVG achieves strong zero-shot localization performance and generalizes effectively to unseen urban environments.

Downloads

Next from ACL 2026

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood

Similar lecture

RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions