United States

Alignment techniques often inadvertently induce sycophancy in LLMs. While prior studies studied this behaviour in direct-answer settings, the role of Chain-of-Thought (CoT) reasoning remains under-explored: does it serve as a logical constraint that mitigates sycophancy, or a tool for post-hoc rationalization that masks it? We evaluate a range of models across objective and subjective tasks to investigate the issue.

Results show that reasoning generally reduces sycophancy in final decisions but also masks sycophancy in some samples, where models construct deceptive justifications through logical inconsistencies, calculation errors, and one-sided arguments etc. Furthermore, LLMs are more prone to sycophancy in subjective tasks and under authority-bias. Our mechanistic analysis reveals that the tendency of sycophancy in LLMs is dynamic during the reasoning process rather than being pre-determined at the input.

ACL 2026

Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy

## 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.

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.

Debate has emerged as a promising oversight mechanism for Large Language Models (LLMs) amid rising systemic complexity, particularly where models outperform human evaluators. Yet, Debate provides little verifiable evidence for its final judgments, and its scalability remains largely unexplored. 

To make oversight grounded and scale as capabilities extend, we introduce an Agentic Oversight framework. By using Dialectic Argumentation as a reasoning function, we extend this paradigm to multilingual and multimodal spaces. We employ a weak-to-strong oversight approach based on two expert models that evaluate and defend contesting answers, while a third blind judge determines the winner using Dialectic Argumentation. Experts argue only for belief-consistent answers, founding the Debate on disagreements. We experimented with six tasks on our framework in both multilingual and multimodal scenarios, and dialectic argumentation consistently outperforms single-expert baselines. Moreover, we show that dialectic judgements from a weaker model deliver argument-mediated supervision that, via fine-tuning, instils unsupervised reasoning signals in expert models.

Agentic Oversight via Dialectic Reasoning

Bargaining is often regarded as a logical arena rather than an art or a matter of intuition, yet Large Language Models (LLMs) still struggle to navigate it due to limited strategic depth and difficulty adapting to complex human factors. Current benchmarks rarely capture this limitation. To bridge this gap, we present a utility feedback centric framework. Our contributions are: (i) AgoraBench, a new benchmark spanning nine challenging settings (e.g., deception, monopoly) that supports diverse strategy modeling; (ii) human-aligned, economically grounded metrics derived from utility theory. This is operationalized via agent utility, negotiation power, and acquisition ratio that implicitly measure how well the negotiation aligns with human preference and (iii) a human preference grounded dataset with learning pipeline that strengthens LLMs’ bargaining ability through both prompting and finetuning. Empirical results indicate that baseline LLM strategies often diverge from human preferences, while our mechanism substantially improves negotiation performance, yielding deeper strategic behavior and stronger opponent awareness.

MERIT Feedback Elicits Better Bargaining in LLM Negotiators

Text-guided image editors can now manipulate authentic medical scans with high fidelity, enabling lesion implantation/removal that threatens clinical trust and safety. Existing defenses are inadequate for healthcare. Medical detectors are largely black-box, while MLLM-based explainers are typically post-hoc, lack medical expertise, and may hallucinate evidence on ambiguous cases. We present MedForge, a data-and-method solution for pre-hoc, evidence-grounded medical forgery detection. We introduce MedForge-90K, a large-scale benchmark of realistic lesion edits across 19 pathologies with expert-guided reasoning supervision via doctor inspection guidelines and gold edit locations. Building on it, MedForge-Reasoner performs localize-then-analyze reasoning, predicting suspicious regions before producing a verdict, and is further aligned with Forgery-aware GSPO to strengthen grounding and reduce hallucinations. Experiments demonstrate state-of-the-art detection accuracy and trustworthy, expert-aligned explanations.

MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning

As multimodal large language models (MLLMs) have advanced to process video inputs, concerns have emerged about their potential for malicious misuse. Prior jailbreak studies have shown that safety alignment in MLLMs can be bypassed through visual inputs, yet it remains unclear which properties of video inputs induce this vulnerability. To address this gap, we introduce Multi-Clip Video (MCV) SafetyBench, a dataset of 2,920 videos designed to evaluate how the diversity of video inputs affects the vulnerability of MLLMs. Each video consists of multiple short clips depicting diverse contexts related to a harmful query. Experiments on eight representative video MLLMs show that attack success consistently increases with the number of clips. Our results further indicate that the video modality is (1) more vulnerable than the image modality, (2) more vulnerable to dynamic videos than to static videos, and (3) more vulnerable when videos contain more diverse contexts. Building on these findings, we propose a defense strategy that leverages the relative robustness of the image modality. Warning: This paper may contain potentially offensive content.

Jailbreaking Multimodal Large Language Models using Multi-Clip Video

The quadratic complexity of attention mechanisms poses a critical bottleneck for large language models processing long contexts. While dynamic sparse attention methods offer input-adaptive efficiency, they face fundamental trade-offs: requiring preprocessing, lacking global evaluation, violating query independence, or incurring high computational overhead. We present RRAttention, a novel dynamic sparse attention method that simultaneously achieves all desirable properties through a head **r**ound-**r**obin (RR) sampling strategy. By rotating query sampling positions across attention heads within each stride, RRAttention maintains query independence while enabling efficient global pattern discovery with stride-level aggregation. Our method reduces complexity from $O(L^2)$ to $O(L^2/S^2)$ and employs adaptive Top-$\tau$ selection for optimal sparsity. Extensive experiments on natural language understanding (HELMET) and multimodal video comprehension (Video-MME) demonstrate that RRAttention recovers over 99\% of full attention performance while computing only half of the attention blocks, achieving 2.4$\times$ speedup at 128K context length and outperforming existing dynamic sparse attention methods. The code is available at [https://github.com/PaddlePaddle/PaddleFleet](https://github.com/PaddlePaddle/PaddleFleet) (see `Research/RRAttention`).

 RRAtention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference

Automating Graphical User Interface (GUI) operations with Multimodal Large Language Models (MLLMs) is promising but remains bottlenecked in real-world long-horizon settings. Key challenges include ensuring precise grounding across diverse interfaces and handling irreversible errors in extended workflows. Current methods often struggle to distinguish targets in low Signal-to-Noise Ratio (SNR) environments and lack sufficient pre-execution verification to prevent error accumulation. To address this, we propose the Memory-augmented Debate System (MaDS). Specifically, MaDS combines: (1) a Dual-Layer Memory Module that integrates universal interaction priors with scenario-specific operational experience to mitigate grounding hallucinations; and (2) Multi-Round Debate that performs pre-execution verification, while transforming execution failures into retrievable Negative Warnings to reduce repeated errors. Additionally, we introduce MaDS-Benchmark, a benchmark for long-horizon mobile GUI tasks with process-oriented evaluation. Experiments show that MaDS achieves a 90.23% Task Success Rate on MaDS-Benchmark and strong performance on public benchmarks including AITW, AITZ, CAGUI, and GUIOdyssey.

MaDS: Long-Horizon GUI Automation via Synergizing Dual-Layer Memory and Multi-Round Debate

Diffusion large language models (dLLMs) offer bidirectional attention and parallel generation, enabling them to exploit global context and naturally support format-constrained tasks like parseable JSON or reasoning templates. While straightforward fixed anchors can enforce such constraints, they often impose rigid spans, leading to truncated reasoning or redundant content. To overcome this, we propose Dynamic Infilling Anchors (DIA), a training-free method that dynamically estimates end-anchor positions to adjust generation length before iterative infilling. This flexible mechanism ensures structural correctness and semantic coherence, avoiding the inefficiencies of fixed-span methods. Experiments on reasoning benchmarks demonstrate that DIA substantially improves format compliance and answer accuracy, achieving significant zero-shot gains on GSM8K and MATH. These results establish DIA as a robust pathway toward reliable, structure-aware generation.

Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models

Vision-language models (VLMs) are increasingly used to make visual content accessible via text-based descriptions. In current systems, however, description specificity is often conflated with their length. We argue that these two concepts must be disentangled: descriptions can be concise yet dense with information, or lengthy yet vacuous. We define specificity relative to a contrast set, where a description is more specific to the extent that it picks out the target image better than other possible images. We construct a dataset that controls for length while varying information content, and validate that people reliably prefer more specific descriptions regardless of length. We find that controlling for length alone cannot account for differences in specificity; it matters how the length budget is applied. These results support evaluation approaches that directly prioritize specificity over verbosity.

 When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation

Interleaved-Modal Chain-of-Thought (I-MCoT) advances vision-language reasoning, such as Visual Question Answering (VQA). This paradigm integrates specially selected visual evidence from the input image into the context of Vision-Language Models (VLMs), enabling them to ground their reasoning logic in these details. Accordingly, the efficacy of an I-MCoT framework relies on identifying *what* to see (evidence selection) and *when* to see it (triggering of insertions). However, existing methods fall short in both aspects. First, for selection, they rely on attention signals, which are unreliable---particularly under severe granularity imbalance between the brief textual query and the informative image. Second, for triggering, they adopt static triggers, which fail to capture the VLMs' dynamic needs for visual evidence. To this end, we propose a novel I-MCoT framework, **A**ctive **I**nformation-driven **M**ulti-modal **C**hain-**o**f-**T**hought (**AIM-CoT**), which aims to improve both evidence selection and insertion triggering via: (1) **Context-enhanced Attention-map Generation (CAG)** to mitigate granularity imbalance via textual context enhancement; (2) **Active Visual Probing (AVP)** to proactively select the most informative evidence via an information foraging process; and (3) **Dynamic Attention-shift Trigger (DAT)** to precisely activate insertions when VLM's attention shifts from text to visual context. Experiments across three benchmarks and four backbones demonstrate AIM-CoT's consistent superiority. Our code is available at https://anonymous.4open.science/r/AIMCoT.

AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning

Medical Multimodal Large Language Models (Med-MLLMs) require egocentric clinical intent understanding for real-world deployment, yet existing benchmarks fail to evaluate this critical capability. We introduce MedGaze-Bench, the first benchmark leveraging clinician gaze as a Cognitive Cursor to assess intent understanding across surgery, emergency simulation, and diagnostic interpretation. Our benchmark addresses three fundamental challenges: visual homogeneity of anatomical structures, strict temporal-causal dependencies in clinical workflows, and implicit adherence to safety protocols. We propose a Three-Dimensional Clinical Intent Framework evaluating: (1) Spatial Intent—discriminating precise targets amid visual noise, (2) Temporal Intent—inferring causal rationale through retrospective and prospective reasoning, and (3) Standard Intent—verifying protocol compliance through safety checks. Beyond accuracy metrics, we introduce Trap QA mechanisms to stress-test clinical reliability by penalizing hallucinations and cognitive sycophancy. Experiments reveal current MLLMs struggle with egocentric intent due to over-reliance on global features, leading to fabricated observations and uncritical acceptance of invalid instructions.

Downloads

Next from ACL 2026

Agentic Oversight via Dialectic Reasoning

Similar lecture

Self-Augmented Preference Alignment for Sycophancy Reduction in LLMs