United States

Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing approaches, the KGW scheme is particularly attractive due to its versatility, efficiency, and effectiveness in natural language generation.
However, KGW&#39;s effectiveness degrades significantly under low-entropy settings such as code generation and mathematical reasoning. A crucial step in the KGW method is random vocabulary partitioning, which enables adjustments to token selection based on specific preferences. Our study revealed that the next-token probability distribution plays an critical role in determining how much, or even whether, we can modify token selection and, consequently, the effectiveness of watermarking.
We refer to this characteristic, associated with the probability distribution of each token prediction, as \emph{watermark strength.} In cases of random vocabulary partitioning, the lower bound of watermark strength is dictated by the next-token probability distribution. However, we found that, by redesigning the vocabulary partitioning algorithm, we can potentially raise this lower bound. In this paper, we propose SSG (\textbf{S}ort-then-\textbf{S}plit by \textbf{G}roups), a method that partitions the vocabulary into two logit-balanced subsets. This design lifts the lower bound of watermark strength for each token prediction, thereby improving watermark detectability. Experiments on code generation and mathematical reasoning datasets demonstrate the effectiveness of SSG.

ACL 2026

 SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking

## 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.

Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing approaches, the KGW scheme is particularly attractive due to its versatility, efficiency, and effectiveness in natural language generation.
However, KGW's effectiveness degrades significantly under low-entropy settings such as code generation and mathematical reasoning. A crucial step in the KGW method is random vocabulary partitioning, which enables adjustments to token selection based on specific preferences. Our study revealed that the next-token probability distribution plays an critical role in determining how much, or even whether, we can modify token selection and, consequently, the effectiveness of watermarking.
We refer to this characteristic, associated with the probability distribution of each token prediction, as \emph{watermark strength.} In cases of random vocabulary partitioning, the lower bound of watermark strength is dictated by the next-token probability distribution. However, we found that, by redesigning the vocabulary partitioning algorithm, we can potentially raise this lower bound. In this paper, we propose SSG (\textbf{S}ort-then-\textbf{S}plit by \textbf{G}roups), a method that partitions the vocabulary into two logit-balanced subsets. This design lifts the lower bound of watermark strength for each token prediction, thereby improving watermark detectability. Experiments on code generation and mathematical reasoning datasets demonstrate the effectiveness of SSG.

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.

**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.

The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integration of retrieved information. This paper proposes to bridge retrieval results and the LLM's reasoning ability through Verbal Annotations, analytic narratives that explicitly articulate the logical connection between a search query and retrieved contexts. Our empirical investigation reveals the potential of Verbal Annotations to substantially enhance the LLM's ability to generate accurate, contextually-grounded responses. Motivated by this finding, we introduce Verbal-R3, a novel agentic RAG framework that consists of a Generator and a Verbal Reranker. The Generator performs iterative retrieval and reasoning, while the Verbal Reranker returns relevance scores and Verbal Annotations to guide the reasoning and answering process of the Generator. The inference process of Verbal-R3 is further refined through relevance-guided test-time scaling, which efficiently allocates test-time compute for effective trajectory expansion. Verbal-R3 achieves state-of-the-art performance on complex Question Answering benchmarks, validating the effectiveness of the proposed framework.

Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning

Reinforcement learning with verifiable rewards (RLVR) typically evaluates only final outcomes, providing limited learning signal about whether the generated reasoning is consistent with the correct answer. As a result, even when ground-truth answers are available during training, on-policy rollouts can repeatedly produce reasoning that is inconsistent with the answer.
We propose Answer-Guided Group Relative Policy Optimization (AG-GRPO) for masked diffusion language models (dLLMs), which generate text through iterative masked-token restoration. AG-GRPO combines standard answer-free (AF) rollouts, sampled without access to the ground-truth answer, with answer-guided (AG) rollouts. In AG rollouts, the model generates reasoning conditioned on an anchored ground-truth answer suffix, and then re-predicts the answer from the generated reasoning for reward computation. We compute group-relative advantages over the combined AF/AG rollout set, allowing answer-guided training signals to improve the answer-free policy used at test time.
Across mathematics, puzzle-solving, and code-generation benchmarks, AG-GRPO consistently improves over the pretrained dLLM and prior RL method for masked dLLMs. We further analyze optimization dynamics to study how shared group-relative advantages support signal transfer and affect convergence. Our code is available at https://github.com/JuHyng/ag_grpo.

AG-GRPO: Answer-Guided GRPO for Masked Diffusion Language Models

Test-time reinforcement learning mitigates the reliance on annotated data by using majority voting results as pseudo-labels, emerging as a complementary direction to reinforcement learning with verifiable rewards (RLVR) for improving reasoning ability of large language models (LLMs). However, this voting strategy often induces confirmation bias and suffers from sparse rewards, limiting the overall performance. In this work, we propose subgroup-specific step-wise confidence-weighted pseudo-label estimation (SCOPE), a framework integrating model confidence and dynamic subgroup partitioning to address these issues. Specifically, SCOPE integrates the proposed step-wise confidence into pseudo-label estimation, prioritizing high-quality reasoning paths over simple frequency count. Furthermore, it dynamically partitions the candidate outputs pool into independent subgroups by balancing reasoning quality against exploration diversity. By deriving local consensus via repeat sampling for each subgroup, SCOPE provides diverse supervision targets to encourage broader exploration. We conduct experiments across various models and benchmarks, experimental results show that SCOPE consistently outperforms recent baselines. Notably, SCOPE achieves relative improvements of 13.1% on challenging AIME 2025 and 8.1% on AMC.

 Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning

Retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate external knowledge at inference. Graph-based RAG extends this by organizing corpora into knowledge graphs, improving multi-hop reasoning and offering a global understanding of the corpus. However, triplet-based graphs generated by LLMs are often fragmented and sparsely connected, which reduces coherence and hinders reasoning. Prior enrichment methods such as clustering, community detection, or approximate graph algorithms attempt to restore connectivity but incur high computational cost and risk semantic distortion. To address these issues, we propose TH-RAG, a hierarchical framework that organizes triplets into subtopics and topics, enhancing connectivity, integrating dispersed information, and supporting robust multi-hop reasoning. Experiments on abstractive and specific QA benchmarks show that TH-RAG outperforms strong baselines in accuracy and robustness while remaining efficient, providing a scalable foundation for graph-based RAG.

TH-RAG : Topic-Based Hierarchical Knowledge Graphs for Robust Multi-hop Reasoning in Graph-based RAG Systems

Despite rapid progress in building conversational AI agents, robustness is still largely untested. Small shifts in user behavior, such as being more impatient, incoherent, or skeptical, can cause sharp drops in agent performance, revealing how brittle current AI agents are. Today’s benchmarks fail to capture this fragility: agents may perform well under standard evaluations but degrade spectacularly in more realistic and varied settings. We address this robustness testing gap by introducing TraitBasis, a lightweight, model-agnostic method for systematically stress testing AI agents. TraitBasis learns directions in activation space corresponding to steerable user traits (e.g., impatience or incoherence), which can be controlled, scaled, composed, and applied at inference time without any fine-tuning or extra data. Using TraitBasis, we extend τ-Bench to τ-bench, where user behaviors are altered via controlled trait vectors. We observe an average 4%–20% performance degradation on τ-bench across frontier models, highlighting the lack of robustness of current AI agents to variations in user behavior. Together, these results highlight both the critical role of robustness testing and the promise of TraitBasis as a simple, data-efficient, and compositional tool. By powering simulation-driven stress tests and training loops, TraitBasis opens the door to building AI agents that remain reliable in the unpredictable dynamics of real-world human interactions. We plan to open-source τ-bench, across four domains: airline, retail, telecom, and telehealth, so the community can systematically QA their agents under realistic, behaviorally diverse intents and trait scenarios.

Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents

Multi-step retrosynthetic planning is a fundamental challenge in organic chemistry, traditionally modeled as a combinatorial search problem guided by single-step prediction models. However, this search-centric paradigm often disconnects from the explicit chemical reasoning processes employed by human experts. In this paper, we propose $R^3$ (Reinforced Reasoning Retrosynthesis), a novel framework that reformulates this task as end-to-end generative reasoning. Instead of traversing a search tree, $R^3$ simulates the problem-solving logic of chemists to directly generate complete synthetic pathways. To achieve this, we initialize the model with domain knowledge and employ end-to-end Reinforcement Learning (RL) to optimize the entire planning policy. Experimental results on Retrobench show that $R^3$ achieves a state-of-the-art Top-1 accuracy of 43.7%, demonstrating that generative reasoning offers a superior alternative to traditional search algorithms in solving complex retrosynthetic problems.

R3: End-to-End Reasoning-based Planning for Multi-step Retrosynthesis via Reinforcement Learning

The efficiency of multi-agent systems driven by large language models (LLMs) largely hinges on their communication topology. However, designing an optimal topology is a non-trivial challenge, as it requires balancing competing objectives such as task performance, communication cost, and robustness. Existing frameworks often rely on static or hand-crafted topologies, which inherently fail to adapt to diverse task requirements, leading to either excessive token consumption for simple problems or performance bottlenecks for complex ones. To address this challenge, we introduce a novel generative framework called \textit{Guided Topology Diffusion (GTD)}. Inspired by conditional discrete graph diffusion models, GTD formulates topology synthesis as an iterative construction process. At each step, the generation is steered by a lightweight proxy model that predicts multi-objective rewards (e.g., accuracy, utility, cost), enabling real-time, gradient-free optimization towards task-adaptive topologies. This iterative, guided synthesis process distinguishes GTD from single-step generative frameworks, enabling it to better navigate complex design trade-offs. We validated GTD across multiple benchmarks, and experiments show that this framework can generate highly task-adaptive, sparse, and efficient communication topologies, significantly outperforming existing methods in LLM agent collaboration. Our code is available at \url{https://anonymous.4open.science/r/diffusion_agent-953C}.

Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models

Mathematical reasoning is one of the core capabilities for Large Language Models (LLMs). Yet, existing approaches often rely on static heuristics or pre-determined reasoning strategies, limiting their ability to adapt to different intermediate states. To address this limitation, we propose FLAIR (Fuzzy-Logic-AssIsted Reasoner), an adaptive framework that integrates fuzzy theory into LLM-based mathematical reasoning. Specifically, FLAIR characterizes intermediate problem-solving states using fuzzy memberships and employs a parameterized fuzzy rule system to conditionally activate subsequent actions. These rule parameters are further adjusted via Reinforcement Learning using solution-level feedback as the reward signal, enabling adaptive and iterative refinement without reliance on a fixed strategy. To the best of our knowledge, this work is the first to integrate fuzzy theory into LLM-based mathematical reasoning. Extensive experiments across multiple benchmarks demonstrate that FLAIR consistently outperforms recent state-of-the-art baselines, while offering effective and interpretable diagnostics of intermediate problem-solving states.

FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner

Mixture-of-Experts (MoE) is a cornerstone for scaling LLMs, yet its training dynamics remain poorly understood, often leading to sub-optimal specialization. Moving beyond static routing, we present a systematic study of the MoE lifecycle using Helmholtz Free Energy}and Router Entropy. We identify a universal Three-Stage Phase Transition—Exploration, Symmetry Breaking, and Stabilization—marked by an Energy Climb and Plateau. This reflects Frustrated Exploration, caused by structural interference between specialization drives and uniformity constraints. To address this, we propose Uncertainty-Aware Routing (UAR), which aligns routing with the model’s epistemic state via: (1) Evidence-Triggered Expansion, increasing active experts for high-energy tokens, and (2) Epistemic Masking, applying load-balancing only in high-uncertainty regimes to shield mature experts. Experiments confirm UAR reduces perplexity and improves expert distinctiveness, offering a principled path toward thermodynamically aligned computation.

 Uncertainty-Aware Routing for Principled Alignment with MoE Dynamics

Large Language Models (LLMs) still struggle with multi-step logical reasoning. Existing approaches either purely refine the reasoning chain in natural language form or attach a symbolic solver as an external module. In this work, we instead ask whether LLMs contain a shared internal logical subspace that simultaneously aligns natural-language and symbolic-language views of the reasoning process. Our hypothesis is that this logical subspace captures logical reasoning capabilities in LLMs that are shared across views while remaining independent of surface forms. To verify this, we employ Canonical Correlation Analysis on the paired residual activations from natural-language and symbolic-language reasoning chains, learning a low-dimensional subspace with maximum cross-view correlation. Furthermore, we design a training-free approach that steers LLMs reasoning chain along this logical subspace, thereby leveraging the complementary reasoning signals from both views. Experiments on four logical reasoning benchmarks demonstrate the effectiveness of our approach, improving accuracy by up to 11 percentage points and generalizing well on out-of-domain problems.

Downloads

Next from ACL 2026

Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning

Similar lecture

Watermarking with Low-Entropy POS-Guided Token Partitioning and Z-Score-Driven Dynamic Bias for Large Language Models