AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

ACL 2026

Timesteps of Mamba Align with Human Reading Times

Yuji Yamamoto, Shinnosuke Isono, Yoshinobu Kawahara, Sho Yokoi

This study demonstrates an alignment of per-word processing time in a popular state-space language model Mamba and human readers. In Mamba, the recurrent state transition at each layer conceptually takes some duration of time, the discretization timestep \Delta_t, determined dynamically in response to the input. Using a naturalistic reading dataset, we show that the per-word timestep from Mamba is a powerful predictor of human reading times, comparable to strong baselines such as word frequency and GPT-2 surprisal and significant even when they are controlled for. We further suggest, through formal analysis of Mamba’s architecture and internal dynamics, that Mamba can serve as a new, valuable lens to look at human real-time language processing with ever-updated memory, because it allows us to look at how each module (layer) weighs short- and long-term information retention, and how noise may interact with dynamic, continuous memory representation. Code is available via an (anonymized) link.

ACL 2026

Lending Eyesight to Language Models: Modeling and Probing Human scanpath through Transformer Decoder

Junlin Li, David Robert Reich, Yu-Yin Hsu

Human scanpaths offer rich and reliable clues about the cognitive mechanisms underlying language comprehension. Decoder-only language models, typically large language models (LLMs), have proven to exhibit striking parallels with human cognitive processes. In this study, we investigate to what extent language models can be endowed with human-like gaze shifts. Besides, by probing scanpath through eye model, analogous to probing language through language models, we ask whether such modeling can yield novel knowledge of the cognitive machinery of sense making.This study presents a novel plug-and-play module, EyeLM, to transform an autoregressive language model into an autoregressive eye model, thus facilitating a probabilistic spatial modeling of human explicit attention. Our EyeLM module, powered by LLMs, achieves competitive performance with novel cognitive probing capabilities. By probing EyeLM, we can reach the predictability and uncertainty of the scanpath. Exhibiting aligned patterns with prior knowledge about human reading comprehension, these probabilistic measures of scanpath act as promising predictors of human comprehension skills.

ACL 2026

Grouped Adaptive Weight Sharing (GAWS): An Inference-Efficient Adaptation Method for Large Language Models

Eman Alsuradi, Junhyun Lee, Kyenghun Lee, Hyeonmok Ko, Fahed Jubair

Although Low-Rank Adaptation (LoRA) revolutionized parameter-efficient fine-tuning, it often incurs an inference overhead due to the extra computation required by adapter layers. While most literature focuses on maximizing accuracy or minimizing parameter counts, this paper prioritizes single-request inference performance in the unmerged adapter setting, where adapters must remain decoupled from the base model at runtime. By analyzing LoRA adapters on GPUs, we identify segmented function calls as the primary source of this latency. To address this, we propose Grouped Adaptive Weight Sharing (GAWS), a novel adapter design based on structured Kronecker product decomposition. Experiments on T5-3B, GPT-2 Large, LLaMA3.2-3B, and RoBERTa-Large show that GAWS reduces latency to about 40% of the gap between the unmerged LoRA and the base model, while maintaining parameter efficiency and comparable accuracy. This positions GAWS as a Pareto-efficient solution for deploying adapted LLMs in latency-sensitive settings, balancing the high latency of compressed adapters with the accuracy of LoRA. The source code is available at:https://github.com/SamsungLabs/GAWS .

ACL 2026

RouterHGC: Optimized Router for LLM-based Multi-Agent Systems via Heterogeneous Graph Contrastive Learning

Yitao Xiao, Shaoyong Guo, Guoming Yang, Qingnan Wang, Yinlin Ren, Xuesong Qiu, Qi Feng

Leveraging powerful planning and reasoning capabilities, Large Language Models (LLMs)-driven Multi-Agent Systems (MAS) have demonstrated remarkable scalability and generalizability across complex tasks. However, dynamically routing the optimal combination of agents and collaboration modes for a given query to balance performance and cost remains challenging. To address the limitation of prior work, which focuses on single-agent settings and overlooks collaborative structures and role assignment in MAS, we propose RouterHGC, the first heterogeneous graph contrastive learning framework for MAS routing. We formalize routing as node selection through edge-weight prediction on a heterogeneous graph whose node types include user queries, collaboration modes, agent roles, and LLMs, with message passing capturing their high-order dependencies. We further design a novel global–local contrastive loss function to jointly optimize graph-level representations and edge-level selections, pulling each query graph toward high-performing positives while pushing it away from underperforming or costly negatives. Experiments on five public datasets covering mathematical reasoning, code generation, and knowledge question answering show that RouterHGC outperforms the best single LLM and baselines, achieving 0.80%–6.17% accuracy gains on MATH and HotpotQA while reducing inference cost by 27.40%.

ACL 2026

Scaling Laws or Threshold Effects: Exploring the Optimal Vocabulary Size for Balancing Performance and Efficiency in Low-Resource Languages

Ao Han, Andong Chen, Yuan Sun, Xiaobing Zhao

While vocabulary expansion scaling laws are well-established for high-resource languages, they remain unverified in low-resource settings. This gap is particularly critical for Byte-level BPE (BBPE), where constrained vocabulary sizes often fail to capture the rich morphemes of complex scripts, leading to severe over-segmentation in languages such as Mongolian, Tibetan, and Uyghur. We systematically investigate jointly-scaled trilingual vocabulary for these languages (140 to 195,000 tokens) across BPE (Llama 2) and BBPE (Qwen2.5/3) architectures. Our results reveal that BBPE follows a “decline-then-rise” pattern, requiring a 9,000-token threshold (3,000 per language) to trigger non-linear performance gains and inference acceleration, whereas BPE improves monotonically. Using Pareto Frontier Analysis, we identify an optimal 79,500-token configuration for BBPE that reduces continuous pre-training duration by over 71% across 1.5B to 8B parameter models while consistently enhancing downstream performance.

ACL 2026

EvoMemKG: An Evolvable Memory Agent for Multi-hop Knowledge Graph Reasoning

Shiyu Tian, Shuyue Xing, Zhuoxin Han, Caixia Yuan, Xiaojie Wang

Integrating knowledge graphs (KGs) with large language models (LLMs) enhances factual accuracy and interpretability in question answering. However, existing agent-based methods rely on static memory mechanisms that fail to address the combinatorial explosion of search spaces in multi-hop reasoning and lack continuous learning capabilities. To overcome these limitations, we propose EvoMemKG, an agent framework with a dynamic, evolvable memory mechanism specifically designed for KG reasoning. EvoMemKG features a dual-layer memory architecture: (1) a working memory that losslessly compresses retrieved triplets through clustering to manage exploration states, effectively linearizing the exponential state space expansion; and (2) an experience memory that abstracts historical reasoning paths into reusable, generalized strategies, enabling cross-task knowledge transfer and self-evolution. We further introduce a double-loop workflow that orchestrates the LLM, memory layers, and KG environment to enable end-to-end autonomous reasoning. Extensive evaluations on three KGQA datasets across two KGs demonstrate that EvoMemKG achieves state-of-the-art performance without requiring additional training or specialized tools. Notably, it achieves improvements of up to 20% over the strong baseline on complex multi-hop queries, validating the effectiveness of our dynamic memory approach.

ACL 2026

Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?

Deokhyung Kang, Seonjeong Hwang, Daehui Kim, Hyounghun Kim, Gary Lee

Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still exhibit a multilingual reasoning gap, performing better in high-resource languages than in low-resource ones. While recent efforts have been made to address this gap, its underlying causes remain largely unexplored. In this work, we show that this gap primarily stems from failures in language understanding—specifically, the model’s inability to translate multilingual inputs into the language dominating its reasoning traces (typically English). As identifying understanding failures can enable targeted mitigation of the gap, we evaluate a range of detection methods and find that understanding failures are detectable to a meaningful extent, with supervised approaches performing best. Building on this, we propose Selective Translation, a strategy that incorporates an English translation into the initial reasoning trace when an understanding failure is detected. Experimental results using Qwen3-4B show that Selective Translation substantially bridges the multilingual reasoning gap, achieving near full-translation performance while translating only about 20% of inputs. Together, our results show that failures in language understanding are the primary driver of the multilingual reasoning gap and can be detected and selectively mitigated, clarifying its origin and suggesting a path toward more equitable multilingual reasoning.

ACL 2026

Trident: Self-Supervised Preference Alignment via Triplet Regularization

Yingnan Guo, Kejia Chen, Xiaofeng Zhang, Zifei Wu, Yu Zhang

Aligning Large Vision-Language Models (LVLMs) to mitigate hallucinations typically relies on high-quality preference data. However, in self-supervised settings, standard binary preference optimization (e.g., DPO) suffers from noisy supervision and semantic ambiguity, as automatically generated chosen responses are not guaranteed to be superior to rejected ones. In this work, we propose Trident, a fully self-supervised framework that ensures robust alignment via a structured triplet paradigm. Trident autonomously constructs reliable preference triplets—comprising semantically enriched (chosen), degraded (rejected), and neutral (anchor) responses—through automated visual perturbations and self-summarization. We further introduce Trident Preference Regularization (TPR), a novel objective that utilizes an adaptive margin to enforce semantic separation between the triplet components while preventing deviation from the pretrained distribution. Despite requiring no human annotations or external reward models, Trident consistently outperforms state-of-the-art RLHF and RLAIF baselines. For instance, on LLaVA-1.5-7B, it reduces the hallucination rate on AMBER to 11.3% and achieves 95.70% precision on POPE using only 4k self-generated triplets and a single epoch. This validates structured triplet supervision as a scalable paradigm for robust self-supervised alignment.

ACL 2026

Leveraging Label Semantics and Entity Description Generation for LLM-based Fine-grained Entity Typing

Yingying Ma, Hongliang Dai, Xia Zhang, Piji Li

Fine-grained entity typing (FET) aims to assign semantically rich and contextually appropriate types to entity mentions. While recent studies have explored the use of large language models (LLMs) for this task, two key challenges persist. First, FET typically involves a large number of entity types, making it difficult for LLMs to perform accurate classification. Second, the presence of label noise in the training data introduced by automatic supervision methods hinders effective fine-tuning. To address these challenges, we propose DR-FET, a descriptor-based retrieval-augmented framework that reduces the effective label space and constructs high-precision training data under noisy supervision. Our method introduces natural language descriptors as an intermediate semantic representation for both entity mentions and types. During inference, entity descriptors are used to retrieve a small set of semantically relevant candidate types, enabling the LLM to perform fine-grained classification under explicit candidate constraints. During training, the same descriptor and retrieval mechanism is reused to identify high-confidence instances from distantly supervised data, prioritizing label precision for efficient fine-tuning. Experiments on two widely used benchmarks demonstrate that the proposed method consistently outperforms existing fine-grained entity typing approaches under noisy supervision.

ACL 2026

Generalizable Prompt Tuning for Audio-Language Models via Semantic Expansion

Jaehyuk Jang, Wonjun Lee, Kangwook Ko, Changick Kim

Prompt tuning has achieved remarkable progress in vision–language models (VLMs) and is recently being adopted for audio–language models (ALMs). However, its generalization ability in ALMs remains largely underexplored. We observe that conventional prompt tuning for ALMs also suffers from the Base–New Tradeoff, and we identify that this issue stems from the disrupted semantic structure of the embedding space. To address this issue, we propose Semantically Expanded Prompt Tuning (SEPT)—a plug-and-play framework that explicitly regularizes the prompt embedding space by incorporating semantic neighbors generated by large language models. SEPT introduces a novel semantic expansion loss with margin constraints that promote intra-class compactness and inter-class separability, thereby enhancing the semantic structure of the prompt embedding space. For comprehensive evaluation, we establish the first benchmark setup for prompt generalization in ALMs, covering both base-to-new generalization and cross-dataset transferability. Extensive experiments demonstrate that SEPT consistently improves generalization performance across multiple prompt tuning baselines, while maintaining computational cost during inference.

ACL 2026

PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs

Jiacheng Wang, Weiyan Zhang, Guangya Yu

Enhancing the task-specific capabilities of Large Language Models (LLMs) primarily requires substantial instruction-tuning datasets. However, the sheer volume of such data imposes a considerable annotation cost, and a lack of optimization methods for tailoring LLMs to specific tasks persists. To address the above issues, we propose a Planning framework for constructing Extractive-based LLMs called PlanE, which includes data decomposition, instruction tuning, and prompt inference. Additionally, we introduce a Data-Tuning-Inference (DTI) planner, aimed at selecting the optimal base-LLM and its DTI combinations for specific datasets to improve construction efficiency. The experimental results demonstrate the effectiveness of our PlanE from two views: (1) across different datasets using the same base-LLM, and (2) on the same dataset using different base-LLMs. Furthermore, we validate the generalizability of the proposed DTI planner under different optimization objectives. The codes are publicly available at https://github.com/gugugu-469/PlanE.

ACL 2026

CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation

Hu Jing, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Shikun Feng, Hai-Tao Zheng, Jingzhou He, Yu Sun, Hua Wu, Haifeng Wang

Large Audio Language Models (LALMs) have garnered significant research interest. Despite being built upon text-based large language models (LLMs), LALMs frequently exhibit a degradation in knowledge and reasoning capabilities. We hypothesize that this limitation stems from the failure of current training paradigms to effectively bridge the acoustic-semantic gap within the feature representation space. To address this challenge, we propose CORD, a unified alignment framework that performs online cross-modal self-distillation. Specifically, it aligns audio-conditioned reasoning with its text-conditioned counterpart within a unified model. Leveraging the text modality as an internal teacher, CORD performs multi-granularity alignment throughout the audio rollout process. At the token level, it employs on-policy reverse KL divergence with importance-aware weighting to prioritize early and semantically critical tokens. At the sequence level, CORD introduces a judge-based global reward to optimize complete reasoning trajectories via Group Relative Policy Optimization (GRPO). Empirical results across multiple benchmarks demonstrate that CORD consistently enhances audio-conditioned reasoning and substantially bridges the audio–text performance gap with only 80k synthetic training samples, validating the efficacy and data efficiency of our on-policy, multi-level cross-modal alignment approach.

ACL 2026

FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning

Xiao Li, Bolin Zhu, Kaiwen Shi, Sichen Liu, Yin Zhu, Yiwei Liu, Gong Cheng

The application of physics formulas is a fundamental human capability in numerical reasoning. While existing datasets often rely on implicit mathematical knowledge, they rarely explicitate the underlying formulas. To address this, we introduce FormulaReasoning, a new benchmark for formula-based numerical reasoning comprising 5,324 questions requiring calculations grounded in external physics principles. We provide high-quality, fine-grained annotations in English and Chinese—including formula structures, parameter names, symbols, values, and units—curated through manual effort and LLM-assisted validation. Additionally, we provide a consolidated formula database as an external knowledge source. To further challenge model performance, we develop an extended version of the dataset by coupling multiple questions. We evaluate various architectural and methodological frameworks, including retrieval-augmented methods, modular reasoning (formula generation, parameter extraction, and calculation), and preference-based optimization. Our analysis identifies critical challenges in formula-based reasoning, highlighting significant opportunities for future methodological advancement.

ACL 2026

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs

Hengran Zhang, Keping Bi, Jiafeng Guo, Xueqi Cheng

Relevance and utility are two frequently used measures to evaluate the effectiveness of an information retrieval (IR) system. Relevance emphasizes the aboutness of a result to a query, while utility refers to the result’s usefulness or value to an information seeker. In Retrieval-Augmented Generation (RAG), high-utility results should be prioritized to feed to LLMs due to their limited input bandwidth. Re-examining RAG’s three core components—relevance ranking derived from retrieval models, utility judgments, and answer generation—aligns with Schutz’s philosophical system of relevances, which encompasses three types of relevance representing different levels of human cognition that enhance each other. These three RAG components also reflect three cognitive levels for LLMs in question-answering. Therefore, we propose an Iterative utiliTy judgmEnt fraMework (ITEM) to promote each step in RAG. We conducted extensive experiments on retrieval (TREC DL, WebAP), utility judgment task (GTI-NQ), and factoid question-answering (NQ) datasets. Experimental results demonstrate significant improvements of in utility judgments, ranking, and answer generation upon representative baselines.

ACL 2026

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

Hao ZHENG, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing presentation agents often rely on predefined workflows and fixed templates. To address this, we present DeepPresenter, an agentic framework that adapts to diverse user intents, enables effective feedback-driven refinement, and generalizes beyond a scripted pipeline. Specifically, DeepPresenter autonomously plans, renders, and revises intermediate slide artifacts to support long-horizon refinement with environmental observations. Furthermore, rather than relying on self-reflection over internal signals (e.g., reasoning traces), our environment-grounded reflection conditions the generation process on perceptual artifact states (e.g., rendered slides), enabling the system to identify and correct presentation-specific issues during execution. Results on the evaluation set covering diverse presentation-generation scenarios show that DeepPresenter achieves state-of-the-art performance, and the fine-tuned DeepPresenter-9B remains highly competitive at substantially lower cost.

ACL 2026

PiCSAR: Probabilistic Confidence Selection and Ranking for Reasoning Chains

Joshua Ong Jun Leang, Zheng Zhao, Aryo Pradipta Gema, Sohee Yang, Wai-Chung Kwan, Xuanli He, Wenda Li, Pasquale Minervini, Eleonora Giunchiglia, Shay B Cohen

Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest reward. The key challenge for reasoning tasks is designing a scoring function that can identify correct reasoning chains without access to ground-truth answers. We propose Probabilistic Confidence Selection and Ranking for Reasoning Chains (PiCSAR): a simple, training-free method that scores each candidate generation using the joint log-likelihood of the reasoning and final answer. This method utilises both the scores of the reasoning path (reasoning confidence) and the final answer (answer confidence). PiCSAR achieves substantial gains across several benchmarks (+11.7 on AIME2024, +9.81 on AIME2025), outperforming baselines with at least 2x fewer samples in 20 out of 25 comparisons. Our analysis reveals that correct reasoning chains exhibit higher reasoning and answer confidence, justifying the effectiveness of PiCSAR.

ACL 2026

XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content

Vadivel Abishethvarman, Bhavik Chandna, Pratik Jalan, Usman Naseem

Large Language Models (LLMs) can generate content spanning ideological rhetoric to explicit instructions for violence. However, existing safety evaluations often rely on simplistic binary labels (safe/unsafe), overlooking the nuanced spectrum of risk these outputs pose. To address this, we present XGUARD, a benchmark and evaluation framework designed to assess the severity of extremist content generated by LLMs on a multi-level grading. It includes 3,840 red-teaming prompts generated using templates informed by real-world extremist scenarios from social media, forums, and news. The framework categorizes model responses into five danger levels (0–4) defined by degree of extremist endorsement, enabling nuanced analysis of failure frequency and severity. We introduce the interpretable Attack Severity Curve (ASC) to visualize vulnerabilities and compare defense mechanisms across threat intensities. Using XGUARD, we evaluate five popular LLMs and two lightweight defense strategies, revealing key insights into current safety gaps and trade-offs between robustness and expressive freedom. Our work underscores the value of graded safety metrics for building trustworthy LLMs. The code and dataset is available at https://github.com/Abishethvarman/XGUARD

ACL 2026

TRUST: Towards Robust Social Bot Detection via Uncertainty-Guided Pseudo-Labeling and Graph Structure Purification

Ruixuan Xu, Mengting Hu, Zhunheng Wang, Ming Jiang, Rui Ying, Zhen Zhang, Hang Gao, Shuaipeng Liu, Renhong Cheng

Social bots threaten online platforms by mimicking human behavior and forming deceptive connections, enabling the dissemination of misinformation while evading detection. Existing graph-based detection models leverage graph neural networks (GNNs) to capture relational structures and multimodal user features. However, such models are vulnerable to deceptive message propagation, where bots deliberately interact with legitimate users. These interactions create heterophilous edges–connections between nodes with different labels (i.e. human and bot)–which undermine the homophily assumption that connected users typically share similar characteristics. In this work, we propose a novel framework to mitigate deceptive message propagation through node-level uncertainty estimation and graph structure purification. The framework comprises three key components: (1) Node uncertainty estimation employs evidential deep learning with an error-sensitive uncertainty loss to obtain calibrated node-wise uncertainty; (2) Uncertainty-guided pseudo-label generation assigns pseudo-labels to low-uncertainty nodes using a dynamic threshold; (3) Graph structure purification selectively disconnects heterophilous edges identified between differently labeled nodes. Extensive experiments on three benchmark datasets and six GNN backbones demonstrate that our framework consistently enhances detection performance and serves as an effective general-purpose enhancement module for social bot detection.

ACL 2026

Anchored Cyclic Generation: A Novel Paradigm for Long-Sequence Symbolic Music Generation

Boyu Cao, Lekai Qian, Dehan Li, Haoyu Gu, Mingda Xu, Qi Liu

Generating long sequences with structural coherence remains a fundamental challenge for autoregressive models across sequential generation tasks. In symbolic music generation, this challenge is particularly pronounced, as existing methods are constrained by the severe error accumulation inherent in autoregressive models, leading to poor performance in music quality and structural integrity. In this paper, we propose the Anchored Cyclic Generation (ACG) paradigm, which relies on anchor features from previously generated musical content to guide subsequent generation during the autoregressive process, effectively mitigating error accumulation in autoregressive methods. Based on the ACG paradigm, we further propose the Hierarchical Anchored Cyclic Generation (Hi-ACG) framework, which employs a systematic global-to-local generation strategy and is highly compatible with our specifically designed piano token, an efficient musical representation. The experimental results demonstrate that compared to traditional autoregressive models, the ACG paradigm reduces cosine distance by an average of 34.7% between predicted feature vectors and ground-truth semantic vectors. In long-sequence symbolic music generation tasks, the Hi-ACG framework significantly outperforms existing mainstream methods in both subjective and objective evaluations. Furthermore, the framework exhibits excellent task generalization capabilities, achieving superior performance in related tasks such as music completion.

ACL 2026

XLSR-MamBo: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detection

Kwok-Ho Ng, Tingting Song, Yongdong WU, Zhihua Xia

Advanced speech synthesis technologies have enabled highly realistic speech generation, posing security risks that motivate research into audio deepfake detection (ADD). While state space models (SSMs) offer linear complexity, pure causal SSMs architectures often struggle with the content-based retrieval required to capture global frequency-domain artifacts. To address this, we explore the scaling properties of hybrid architectures by proposing XLSR-MamBo, a modular framework integrating an XLSR front-end with synergistic Mamba-Attention backbones. We systematically evaluate four topological designs using advanced SSM variants, Mamba, Mamba2, Hydra, and Gated DeltaNet. Experimental results demonstrate that the MamBo-3-Hydra-N3 configuration achieves competitive performance compared to other state-of-the-art systems on the ASVspoof 2021 LA, DF, and In-the-Wild benchmarks. This performance benefits from Hydra’s native bidirectional modeling, which captures holistic temporal dependencies more efficiently than the heuristic dual-branch strategies employed in prior works. Furthermore, evaluations on the DFADD dataset demonstrate robust generalization to unseen diffusion- and flow-matching-based synthesis methods. Crucially, our analysis reveals that scaling backbone depth effectively mitigates the performance variance and instability observed in shallower models. These results demonstrate the hybrid framework’s ability to capture artifacts in spoofed speech signals, providing an effective method for ADD. Codes are publicly available at https://github.com/saki-ciallo/XLSR-MamBo.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.