United States

Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated remarkable effectiveness in boosting the objective performance (e.g., reasoning) of Large Language Models (LLMs) through rule-based, on-policy self-improvement strategies. However, optimizing LLMs for subjective capabilities and alignment with human preferences remains challenging due to the non-verifiable nature. Most prior works use datasets comprising response pairs with substantial quality gaps labeled by a strong external judge. While effective for preference metrics, this paradigm often incurs an ``alignment tax&#39;&#39;, where the model&#39;s objective performance on downstream tasks degrades as it overfits to subjective preferences. In this work, we introduce Donkey, a high-quality, non-verifiable dataset where response pairs differ only by subtle nuances. We find that LLMs optimized on Donkey via preference learning outperform those trained on data with explicit quality gaps, while simultaneously maintaining their objective capabilities. Furthermore, we observe that preference signals on Donkey can be decomposed into consensus preferences and individual preferences. Our analysis reveals that distilling consensus preferences provides a significantly more data-efficient signal for preference optimization. Our findings underscore the importance of leveraging nuanced preference signals and the consensus of multiple judges for advancing subjective LLM alignment. Our code and data will be available at https://github.com/SJY8460/Donkey.

ACL 2026

From Individual to Common: An Early Exploration of Consensus in Non-verifiable Data for Balanced Preference Optimization

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

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 AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

AAAI 2026

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated remarkable effectiveness in boosting the objective performance (e.g., reasoning) of Large Language Models (LLMs) through rule-based, on-policy self-improvement strategies. However, optimizing LLMs for subjective capabilities and alignment with human preferences remains challenging due to the non-verifiable nature. Most prior works use datasets comprising response pairs with substantial quality gaps labeled by a strong external judge. While effective for preference metrics, this paradigm often incurs an ``alignment tax'', where the model's objective performance on downstream tasks degrades as it overfits to subjective preferences. In this work, we introduce Donkey, a high-quality, non-verifiable dataset where response pairs differ only by subtle nuances. We find that LLMs optimized on Donkey via preference learning outperform those trained on data with explicit quality gaps, while simultaneously maintaining their objective capabilities. Furthermore, we observe that preference signals on Donkey can be decomposed into consensus preferences and individual preferences. Our analysis reveals that distilling consensus preferences provides a significantly more data-efficient signal for preference optimization. Our findings underscore the importance of leveraging nuanced preference signals and the consensus of multiple judges for advancing subjective LLM alignment. Our code and data will be available at https://github.com/SJY8460/Donkey.

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

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

Writing is a cognitively demanding activity that requires constant decision-making, heavy reliance on working memory, and frequent shifts between tasks of different goals. To build writing assistants that truly align with writers' cognition, it is necessary to capture and analyze the complete thought process behind how writers transform ideas into final texts. We present SCHOLAWRITE, the first dataset of end-to-end scholarly writing, tracing the multi-month journey from initial drafts to final manuscripts. The dataset traces nearly 62K LaTeX-based edits from five computer science preprints over four months and is enriched with fine-grained annotations of cognitive writing intentions. We demonstrate the value of ScholaWrite through three complementary contributions: (1) analysis of real-world writing behavior reveals that scholarly writing is highly non-linear and multi-intentional, blending rapid drafting bursts with cognitively sustained writing sessions; (2) evaluations of current large language models show that they struggle to provide meaningful support throughout the human writing process; and (3) models finetuned on SCHOLAWRITE demonstrate improved alignment with human writing workflows. SCHOLAWRITE underscores the value of capturing scientists' cognitive writing process and provides actionable insights and resources for the development of future writing assistants.

ScholaWrite: A Dataset of End-to-End Scholarly Writing

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due to the quadratic complexity of softmax attention and the growing Key-Value (KV) cache that makes inference memory-bound by context length. Lizard addresses these limitations by introducing a subquadratic attention mechanism that closely approximates softmax attention while preserving model quality. Unlike prior linearization methods constrained by fixed, non-adaptive structures, Lizard augments the architecture with compact, learnable modules that enable adaptive memory control and robust length generalization. Moreover, we introduce a hardware-aware algorithm that solves numerical instability in gated attention to accelerate training. Extensive experiments show that Lizard achieves near-lossless recovery of its teacher model's performance, significantly outperforming previous methods by up to 9.4 - 24.5 points on the 5-shot MMLU benchmark and demonstrating superior associative recall.

 Lizard: An Efficient Linearization Framework for Large Language Models

Large language models (LLMs) are playing an increasingly pivotal role in LegalAI. However, existing benchmarks are primarily tailored for legal professionals, emphasizing deep reasoning and explainability. While public-facing legal applications demand outputs that are direct, actionable, and accessible, a need largely overlooked by current evaluation frameworks. To bridge this gap, we propose a public-oriented LegalAI benchmark grounded in legal functionalism and genre analysis. Specifically, we categorize public legal demands into two core tasks: Instant Question Answering and Legal Text Generation. We further introduce three public-oriented evaluation dimensions: legal normativity, content relevance, and format usability, which collectively assess the practical validity and user readiness of model outputs. To reflect real-world lay user usage, we evaluate 17 LLMs on Pub-LawBench using only simple prompts and Chain-of-Thought under a vanilla inference setting, excluding complex techniques like RAG or agent-based methods inaccessible to non-experts. Experiments reveal limitations of current LLMs in delivering effective public-oriented legal assistance, highlighting the need for more user-centric model development and benchmarking. Our code and datasets are available for review at https://anonymous.4open.science/r/P-LawBench-E565/.

Pub-LawBench: Public-Oriented Benchmarking for LegalAI

Post-cutoff performance decay has been widely interpreted as a temporal signal for benchmark contamination.
We critically examine this belief and demonstrate that this temporal signal is highly sensitive to how benchmark questions are constructed.
Specifically, we show that LLM-generated questions can produce remarkably different temporal patterns compared to fill-in-the-blank questions directly retrieved from the very same materials.
We validated this finding on previous benchmarks that reported clear post-cutoff performance decay such as LiveCodeBench and further showed simple LLM transformation could effectively remove this temporal pattern when evaluated on the same models.
We also provide a mechanistic understanding of our observation using influence function analysis.
Overall, this work offers a new perspective on the sensitivity of temporal contamination signal and highlights the need for more robust contamination detection methods for reliable AI evaluation.

 Test of Time: Rethinking Temporal Signal of Benchmark Contamination

Dynamic tool generation empowers Large Language Model (LLM) agents to synthesize tools on demand, yet a critical challenge remains: 32.4\% of generated tools fail on first invocation. We present Causal Tool Diagnosis (CTD), a principled framework that moves beyond black-box reliability prediction to interpretable failure attribution. CTD constructs a Structural Causal Model (SCM) capturing how specification quality, code characteristics, and execution environment jointly determine tool outcomes. Uniquely leveraging code's intervenability, we conduct controlled sandbox experiments to estimate causal effects---an advantage unavailable in pure text generation. CTD jointly predicts confidence (Spearman rank correlation coefficient $\rho$=0.90) and root cause attribution (78\% accuracy), with attributions directly guiding targeted repairs (+9.6\% success rate over error-type classification). Our ARCHITECT framework, integrating CTD throughout the tool lifecycle, achieves state-of-the-art on four benchmarks including StableToolBench (+3.8\%), MINT (+4.6\%), T-Eval (+3.7\%), and SWE-bench Lite (+2.4\%), with consistent improvements across all settings.

ARCHITECT: Uncertainty-Aware Dynamic Tool Learning via Causal Intervention for Open-World Agents

A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains critically underdeveloped in current Large Multi-modal Models (LMMs). The deficiency is often masked by evaluation metrics that prioritize final-answer accuracy, creating an illusion of competence where genuine reasoning is absent. Using the domain of geometric problem-solving as a precise instrument, we probe this issue through tasks that require constructing visual aids.To this end, we introduce \textbf{VisAidMath}, a challenging benchmark, and our novel Three-Layered Funnel Evaluation Framework. This framework moves beyond simple accuracy (ACCU) to scrutinize the generation of valid visual aids (PVA) and the soundness of subsequent reasoning steps (SPRS). Our extensive experiments on state-of-the-art models, including Doubao-Seed-1.6 and o4, reveal a profound ``Reasoning Illusion''. We observe that high surface-level accuracy conceals a catastrophic failure in the models' ability to produce valid visual aids or to reason from them. Our findings expose a fundamental schism between visual perception and logical deduction in modern LMMs. We provide a public evaluation platform on CodaBench and release the project homepage.

VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning

The growing demand for efficient and lightweight Retrieval-Augmented Generation (RAG) systems has highlighted significant challenges when deploying Small Language Models (SLMs) in existing RAG frameworks. Current approaches face severe performance degradation due to SLMs' limited semantic understanding and text processing capabilities, creating barriers for widespread adoption in resource-constrained scenarios. To address these fundamental limitations, we present MiniRAG, a novel RAG system designed for simplicity and efficiency. MiniRAG introduces two key technical innovations: (1) a semantic-aware heterogeneous graph indexing mechanism that combines text chunks and named entities in a unified structure, reducing reliance on complex semantic understanding, and (2) a lightweight topology-enhanced retrieval approach that leverages graph structures for efficient knowledge discovery without requiring advanced language capabilities. Our extensive experiments demonstrate that MiniRAG achieves comparable performance to LLM-based methods even when using SLMs while requiring only 25% of the storage space. Additionally, we contribute a comprehensive benchmark dataset for evaluating lightweight RAG systems under realistic on-device scenarios with complex queries.

MiniRAG: A Lightweight RAG system with Small Language Models

Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning, these findings were limited to finetuning and activation steering, leaving out in-context learning (ICL). We therefore ask: does EM emerge in ICL? We find that it does: across four model families (Gemini, Kimi-K2, Grok, and Qwen), narrow in-context examples cause models to produce misaligned responses to benign, unrelated queries. With 16 in-context examples, EM rates range from 1\% to 24\% depending on model and domain, appearing with as few as 2 examples. Neither larger model scale nor explicit reasoning provides reliable protection, and larger models are typically even more susceptible. Next, we formulate and test a hypothesis, which explains in-context EM as conflict between safety objectives and context-following behavior. Consistent with this, instructing models to prioritize safety reduces EM while prioritizing context-following increases it. These findings establish ICL as a previously underappreciated vector for emergent misalignment that resists simple scaling-based solutions.

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Although the Universal Transformer (UT) mitigates the diminishing returns of standard LLM scaling by decoupling parameter count from depth, it remains constrained by linear computational costs and rigid weight-sharing mechanisms. These limitations lead to severe functional homogeneity, which subsequently induces over-smoothing, representation rank collapse, and degraded reasoning performance. In this work, we present the first systematic study of Compute Distribution Skew, identifying it as the primary driver of extrapolation failure. This is a pathological phenomenon in ultra-deep recurrent Transformers characterized by a disproportionate distribution of contributions across recurrent steps, resulting in distinct functional states during prefix and suffix processing phases. To address this challenge, we propose the Polymorphic Transformer, which aims to achieve functional polymorphism and depth sparsity within a shared-parameter framework. By integrating conditional sparse subspaces, SiLU Attention, and an uncertainty-aware depth scheduler, our architecture mitigates power-method collapse and effectively decouples logical depth from computational cost. Experiments demonstrate that our model significantly enhances representation rank and robustness, achieving complex reasoning performance comparable to baseline while reducing computation by 64.7%.

 Polymorphic Universal Transformer

Current evaluations of geospatial reasoning in LLMs are frequently impeded by the entanglement of factual recall and spatial logic, which often obscures the models' true capabilities in complex city-scale environments. To address this, we introduce UrbanGeoEval, a comprehensive benchmark featuring a dual-module framework designed to disentangle these competencies. The Knowledge Module assesses urban memory via scalable map-based queries, while the Reasoning Module isolates pure logical inference across 3,148 realistic tasks by providing necessary geospatial context. Unlike prior benchmarks that hand the model pre-computed spatial text, UrbanGeoEval provides raw geometry and forces the model to act as a spatial computing engine. Our evaluation methodology introduces a reliable hybrid pipeline that merges deterministic programmatic checks with an LLM-as-a-Judge, achieving expert-level evaluation accuracy. Extensive experiments on 18 widely used LLMs uncover critical insights: (1) models exhibit severe geographic biases and resolution gaps; (2) failures in complex multi-hop tasks often stem from brittle foundational spatial skills rather than high-level logic deficits. UrbanGeoEval provides a precise diagnostic tool for advancing urban geospatial intelligence in LLMs.

Downloads

Next from ACL 2026

ScholaWrite: A Dataset of End-to-End Scholarly Writing

Similar lecture

SMPRO: Self-Supervised Visual Preference Alignment via Differentiable Multi-Preference Multi-Group Ranking

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES