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

PhageBench: Can LLMs Understand Raw Bacteriophage Genomes?

Yusen Hou, Weicai Long, Haitao Hu, houcheng su, Junning Feng, Yanlin Zhang

Bacteriophages, often referred to as the dark matter of the biosphere, play a critical role in regulating microbial ecosystems and in antibiotic alternatives. Thus, accurate interpretation of their genomes holds significant scientific and practical value. While general-purpose Large Language Models (LLMs) excel at understanding biological texts, their ability to directly interpret raw nucleotide sequences and perform biological reasoning remains underexplored. To address this, we introduce PhageBench, the first benchmark designed to evaluate phage genome understanding by mirroring the workflow of bioinformatics experts. The dataset contains 5,600 high-quality samples covering five core tasks across three stages: Screening, Quality Control, and Phenotype Annotation. Our evaluation of eight LLMs reveals that general-purpose reasoning models significantly outperform random baselines in phage contig identification and host prediction, demonstrating promising potential for genomic understanding. However, they exhibit significant limitations in complex reasoning tasks involving long-range dependencies and fine-grained functional localization. These findings highlight the necessity of developing next-generation models with enhanced reasoning capabilities for biological sequences.

ACL 2026

Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition

Qi Zhang, Fangping Lan, Cornelia Caragea, Longin Jan Latecki, Eduard Dragut

In-context learning (ICL) with large language models (LLMs) has emerged as a powerful alternative to fine-tuning for Named Entity Recognition (NER), achieving strong performance with minimal annotation and no additional training. However, prior work has shown that despite their adaptability, LLMs still lag behind fully supervised models such as fine-tuned BERT in structured tasks like NER. While existing studies on ICL for NER have mainly explored few-shot settings, the potential of scaling to hundreds of demonstrations has not been thoroughly investigated. To address this gap, we conduct a comprehensive investigation of many-shot ICL for NER and further explore its effectiveness in annotating and refining data for low-resource NER tasks. Specifically, we evaluate various LLMs across multiple domains using hundreds of ICL examples and then assess the feasibility of using many-shot ICL as a data annotation framework. Our experiments demonstrate that: (1) scaling to hundreds of in-context examples enables LLMs to match or even surpass the performance of fully supervised BERT models; and (2) using about one hundred human-labeled examples as demonstrations, many-shot in-context annotation can generate high-quality labeled data, leading to approximately 10% absolute F1 improvement over existing state-of-the-art approaches when used to fine-tune BERT on low-resource NER.

ACL 2026

LayerNorm Induces Recency Bias in Transformer Decoders

Junu Kim, Xiao Liu, Zhenghao Lin, Lei Ji, Yeyun Gong, Edward Choi

Causal self-attention provides positional information to Transformer decoders. Prior work has shown that stacks of causal self-attention layers alone induce a positional bias in attention scores toward earlier tokens. However, this differs from the bias toward later tokens typically observed in Transformer decoders, known as recency bias. We address this discrepancy by analyzing the interaction between causal self-attention and other architectural components. We show that stacked causal self-attention layers combined with LayerNorm induce recency bias. Furthermore, we examine the effects of residual connections and the distribution of input token embeddings on this bias. Our results provide new theoretical insights into how positional information interacts with architectural components and suggest directions for improving positional encoding strategies.

ACL 2026

Towards semantic reliable clinical QA: Query pipeline optimization for cancer patient question answering systems

MaoLin He, Rena Wei Gao, Mike Conway, Brian E. Chapman

Large Language Models (LLMs) show promise in medical Question-Answering (QA) but suffer from hallucinations that jeopardize patient safety. While Retrieval-Augmented Generation (RAG) mitigates this by grounding outputs in external evidence, existing pipelines struggle with the complex, rapidly evolving nature of oncology. We present CoMeta, a three-level controllable metadata-aware framework optimized for Cancer Patient QA (CPQA). We introduce Clinical Hybrid Semantic-Symbolic Document Retrieval (CHSDR), which synergizes real-time Boolean search via NCBI E-Utilities with semantic retrieval to overcome metadata blindness. Additionally, we propose Semantic Enhanced Overlap Segmentation (SEOS) to prevent contextual fragmentation. Our results demonstrate that CHSDR significantly improves retrieval performance, CoMeta improved the answer accuracy of Claude-3-haiku by 5.24% over chain-of-thought prompting and about 3% over a naive RAG setup. This study highlights the importance of domain-specific query optimization in realizing the full potential of RAG and provides a robust framework for building more reliable CPQA systems.

ACL 2026

TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization

Shichao Ma, Zhiyuan Ma, Ming Yang, Xiaofan Li, Xing Wu, Jintao Du, Yu Cheng, Weiqiang Wang, Qiliang Liu, Zhengyang Zhou, Yang Wang

Multi-turn tool-integrated reasoning enables Large Language Models (LLMs) to solve complex tasks through iterative information retrieval. However, current reinforcement learning (RL) frameworks for search-augmented reasoning predominantly rely on sparse outcome-level rewards, leading to a “Double Homogenization Dilemma.” This manifests as (1) Process homogenization, where the thinking, reasoning, and tooling involved in generation are ignored. (2) Intra-group homogenization, coarse-grained outcome rewards often lead to inefficiencies in intra-group advantage estimation with methods like Group Relative Policy Optimization (GRPO) during sampling. To address this, we propose Turn-level Stage-aware Policy Optimization (TSPO). TSPO introduces the First-Occurrence Latent Reward (FOLR) mechanism, allocating partial rewards to the step where the ground-truth answer first appears, thereby preserving process-level signals and increasing reward variance within groups without requiring external reward models or any annotations. Extensive experiments demonstrate that TSPO significantly outperforms state-of-the-art baselines, achieving average performance gains of 24% and 13.6% on Qwen2.5-3B and 7B models, respectively. Code is available at https://github.com/Flipped-May/TSPO.

ACL 2026

MDTeamGPT: Mitigating Context Collapse and Enabling Self-Evolution in Medical Multi-Agent Reasoning

Kai Chen, Xinfeng Li, Tianpei Yang, Hewei Wang, Guang Yang, Jing Huo, Yang Gao

Large language models (LLMs) have shown great potential in multi-disciplinary team (MDT) medical consultations. However, long, multi-round, multi-role interaction trajectories inevitably lead to severe information dilution and context window overload, triggering context collapse which destabilizes reasoning. Furthermore, prior systems typically rely on unstructured trajectory history storage without structurally distilling key information or reflecting on errors, severely limiting continuous learning capabilities. We propose MDTeamGPT, a context-resilient and self-evolving multi-agent framework. Mechanistically, we introduce a specialized Lead Physician mechanism combined with a Residual Context architecture to compress and reorganize multi-round consensus, effectively mitigating context overload and reducing computational costs. For memory, we design a Dual Knowledge Base system comprising a CorrectKB for verified trajectories and a ChainKB for reflective error analysis, enabling self-evolution via retrieval from both successes and failures. We evaluated our framework on standard text datasets (MedQA, PubMedQA), multimodal benchmarks (VQA-RAD, SLAKE), and collected more complex clinical problems. Experimental results show that MDTeamGPT substantially outperforms existing baselines across both text-based and multimodal tasks, while also demonstrating superior diagnostic performance and stability in complex clinical scenarios.

ACL 2026

LLM-induced Rationales for More Compact Explainable Style Classification Models

Ahmad Aljanaideh, Saeb Ganideh

The complexity of recent natural language classification models led to interest in developing methods for improving the performance of explainable models (e.g. Logistic Regression). Existing methods focus on clustering word embeddings to discover fine-grained contextual features that can be used to train a linear model. While those methods help reduce the gap in performance between black-box models and explainable models, they are based on discovering a large number of features, and this affects interpretability. In this work, we propose a model that leverages Large Language Models (LLMs) and clustering algorithms to discover a compact set of interpretable features. The proposed model first uses GPT-4o mini to extract rationales (i.e. phrases which explain an item’s label) from labeled text, and then clusters those rationales to obtain a compact, interpretable feature space. Across 3 Style Classification tasks, the resulting features achieve comparable performance to word-cluster baselines on most tasks, while reducing the number of features by 85–99%. These results highlight the potential of LLMs to improve the compactness of explainable AI models.

ACL 2026

ERRV: Eliciting Efficient Reasoning through Reasoning Vectors for Policy Optimization in Large Language Models

Zhuowen Han, Lei Yang, Renren Jin, Dan Shi, Chenxi Sun, Deyi Xiong

Recently, large reasoning models have achieved impressive performance, but their lengthy reasoning processes incur substantial inference overhead. To mitigate this issue, we propose the concept of reasoning vectors, representations extracted from the model’s hidden states, which can guide the model towards generating more concise and accurate responses. Building upon this, we present ERRV, a training framework that elicits efficient reasoning through reasoning vectors, which enables the model to generate high-quality responses during reinforcement learning. By performing targeted policy optimization on both accuracy and length objectives, ERRV effectively activates the model’s latent capability for efficient reasoning. Our experiments demonstrate that after training with ERRV, the model achieves approximately 30% reduction in reasoning length while maintaining stable accuracy, without guidance from the reasoning vector during inference. This establishes a trade-off between efficiency and performance. Furthermore, we identify key properties of reasoning vectors: robustness, characterized by high similarity before and after training, and generalizability, demonstrating applicability across base models, distilled models, RL-trained models, parameter-merged models, and mixed-thought models. These properties collectively guarantee the reliability and broad applicability of our approach.

ACL 2026

From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning

Xiaoyu Xu, Minxin Du, Zitong Li, Zi Liang, Zhibiao Guo, Zhang Shiyu, Peizhao Hu, Qingqing Ye, Haibo Hu

Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfully represent the true “forgetting scope” learned by the model. We formalize two distinct unlearning granularities, domain-level and instance-level, and propose , an automated framework for synthesizing high-quality forget sets.Unlike prior work relying on external generators, exploits the target model per se to elicit data that matches its internal knowledge distribution through seed-guided and adversarial prompting. Our experiments across diverse benchmarks show that it achieves a superior balance of relevance, diversity, and efficiency. Quantitatively, in the Harry Potter domain, it improves relevance by {\sim}20 and diversity by {\sim}0.05 while halving the total data size compared to SOTAs. Ultimately, it facilitates more robust forgetting and better utility preservation, providing a more rigorous foundation for evaluating LLM unlearning.

ACL 2026

MAKI: Multi-layer Aligned Knowledge Injection for Structure-aware Knowledge Graph Completion with Large Language Models

Zhiwen Xie, Xin Wang, Guangyou Zhou, Derek F. Wong

Recent advances in large language models (LLMs) have shown strong potential for knowledge graph completion (KGC). However, existing LLM-based approaches often struggle to effectively capture the structural information in knowledge graphs (KGs), leading to suboptimal reasoning performance. To address this challenge, we propose a Multi-layer Aligned Knowledge Injection (MAKI) model, a novel method that tightly integrates structured KG information into LLMs through multi-layer alignment. Specifically, we first leverage LLMs to encode the textual information of entities and relations, obtaining their semantic representations across multiple hidden layers. We then introduce a multi-layer aligned structure learning module, which uses graph neural networks (GNNs) to learn relational structures while aligning with the corresponding LLM layers to bridge the gap between structural and semantic spaces. Finally, a gated fusion mechanism is used to inject the structured knowledge into the LLM for reasoning over candidate triples. Experimental results on various benchmark datasets demonstrate that the proposed MAKI outperforms existing state-of-the-art methods.

ACL 2026

Reducing Peak Memory Usage for Modern Multimodal Large Language Model Pipelines

Junwan Kim, Hyunkyung Bae

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale to richer visual representations, inference increasingly relies on storing large numbers of vision tokens in the key–value (KV) cache, making memory consumption a central bottleneck. Existing methods address this issue by identifying redundancy in vision tokens and compressing the cache, but such compression is typically applied only after all inputs are processed, resulting in high peak memory usage during the prefill stage. In this work, we show that MLLMs exhibit inherent structural regularities and representational redundancy that can be exploited to control memory growth throughout inference. Based on this insight, we propose a sequential input-compression mechanism that enforces a fixed memory budget by performing structure-aware key–value cache compression during the prefill process. This approach substantially reduces peak memory usage while maintaining generative performance with only minimal degradation, enabling more practical and memory-efficient multimodal inference.

ACL 2026

When Backdoors Go Beyond Triggers: Semantic Drift in Diffusion Models Under Encoder Attacks

Shenyang Chen, Liuwan Zhu

Standard evaluations of backdoor attacks on text-to-image (T2I) models primarily measure trigger activation and visual fidelity. We challenge this paradigm, demonstrating that encoder-side poisoning induces persistent, trigger-free semantic corruption that fundamentally reshapes the representation manifold. We trace this vulnerability to a geometric mechanism: a Jacobian-based analysis reveals that backdoors act as low-rank, target-centered deformations that amplify local sensitivity, causing distortion to propagate coherently across semantic neighborhoods. To rigorously quantify this structural degradation, we introduce SEMAD (Semantic Alignment and Drift), a diagnostic framework that measures both internal embedding drift and downstream functional misalignment. Our findings, validated across diffusion and contrastive paradigms, expose the deep structural risks of encoder poisoning and highlight the necessity of geometric audits beyond simple attack success rates.

ACL 2026

From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs

Shaojie Wang, Liang Zhang

Recent studies reveal that large language models (LLMs) exhibit limited logical reasoning abilities in mathematical problem-solving, instead often relying on pattern-matching and memorization. We systematically analyze this limitation, focusing on logical relationship understanding, which is a core capability underlying genuine logical reasoning, and reveal that errors related to this capability account for over 90% of incorrect predictions, with Chain-of-Thought Supervised Fine-Tuning (CoT-SFT) failing to substantially reduce these errors. To address this bottleneck, we propose First-Step Logical Reasoning (FSLR), a lightweight training framework targeting logical relationship understanding. Our key insight is that the first planning step-identifying which variables to use and which operation to apply-encourages the model to derive logical relationships directly from the problem statement. By training models on this isolated step, FSLR provides explicit supervision for logical relationship understanding, unlike CoT-SFT which implicitly embeds such relationships within complete solution trajectories. Extensive experiments across multiple models and datasets demonstrate that FSLR consistently outperforms CoT-SFT under both in-distribution and out-of-distribution settings, with average improvements of 3.2% and 4.6%, respectively. Moreover, FSLR achieves 4-6× faster training and reduces training token consumption by over 80%.

ACL 2026

Feedback Adaptation for Retrieval-Augmented Generation

Jihwan Bang, Seunghan Yang, Kyuhong Shim, Simyung Chang, Juntae Lee, Sungha Choi

Retrieval-Augmented Generation (RAG) systems are typically evaluated under static assumptions, despite being frequently corrected through user or expert feedback in deployment. Existing evaluation protocols focus on overall accuracy and fail to capture how systems adapt after feedback is introduced. We introduce feedback adaptation as a problem setting for RAG systems, which asks how effectively and how quickly corrective feedback propagates to future queries. To make this behavior measurable, we propose two evaluation axes: correction lag, which captures the delay between feedback provision and behavioral change, and post-feedback performance, which measures reliability on semantically related queries after feedback. Using these metrics, we show that training-based approaches exhibit a trade-off between delayed correction and reliable adaptation. We further propose PatchRAG, a minimal inference-time instantiation that incorporates feedback without retraining, demonstrating immediate correction and strong post-feedback generalization under the proposed evaluation. Our results highlight feedback adaptation as a previously overlooked dimension of RAG system behavior in interactive settings.

ACL 2026

VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models

Hanling Zhang, Yayu Zhou, Tongcheng Fang, Zhihang Yuan, Guohao Dai, Wanli Ouyang, Yu Wang

Small Language Models (SLMs) provide computational advantages in resource-constrained environments, yet memory limitations remain a critical bottleneck for edge device deployment. A substantial portion of SLMs’ memory footprint stems from vocabulary-related components, particularly embeddings and language modeling (LM) heads, due to large vocabulary sizes. Existing static vocabulary pruning, while reducing memory usage, suffers from rigid, one-size-fits-all designs that cause information loss during the prefill stage and lack flexibility. In this work, we identify two key principles underlying the vocabulary reduction challenge: the lexical locality principle, the observation that only a small subset of tokens is required during any single inference, and the asymmetry in computational characteristics between vocabulary-related components of SLM. Based on these insights, we introduce VocabTailor, a novel decoupled dynamic vocabulary selection framework that addresses memory constraints through offloading embedding and implements a hybrid static-dynamic vocabulary selection strategy for LM Head, enabling on-demand loading of vocabulary components. Comprehensive experiments across diverse downstream tasks demonstrate that VocabTailor achieves a reduction of up to 99% in the memory usage of vocabulary-related components with minimal or no degradation in task performance, substantially outperforming existing static vocabulary pruning. Our code is available at https://github.com/AwakenedInsects/VocabTailor.

ACL 2026

OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces

Xiaozhe Li, Jixuan Chen, Xinyu Fang, Shengyuan Ding, Haodong Duan, Qingwen Liu, Kai Chen

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential for problem-solving—perception, reasoning, and memory—remain the stable core of intelligence. Unlike memorizing specific patterns, humans succeed in novel environments by applying these intrinsic faculties to adapt and optimize. Yet, whether LLMs possess this essential capacity—namely, the ability to continuously refine solutions in response to dynamic environmental feedback—remains underexplored. To address this challenge, we introduce OPT-BENCH, a benchmark for evaluating self-improvement capabilities in large-scale search spaces. By combining 20 machine learning tasks with 10 classic NP-hard problems, OPT-BENCH provides a rigorous setting to assess whether agents can adapt through intrinsic self-reflection rather than rote tool application. We further propose OPT-Agent, a framework that emulates human-like cognitive adaptation. It operates via a general perception–memory–reasoning loop, iteratively refining solutions based on environmental feedback. Through extensive experiments on 19 LLMs from 7 model families, including reasoning models, general models, and open-source models ranging from 3B to 235B parameters, we demonstrate stronger models are more effective at leveraging feedback signals for self-improvement. However, this upper-bound adaptability remains fundamentally constrained by the models’ base capacity, and even the most advanced LLMs still fall short of human expert performance.

ACL 2026

Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models

Mohammad Mahdi Abootorabi, Omid Ghahroodi, Anas Madkoor, Marzia Nouri, Doratossadat Dastgheib, Ehsaneddin Asgari

Despite the rapid progress of Vision-Language Models (VLMs), the field lacks benchmarks that rigorously diagnose their true reasoning abilities and chart meaningful progress toward human-like multimodal intelligence. Most existing evaluations focus on piecemeal or disconnected tasks, obscuring critical cognitive weaknesses and providing little insight for targeted improvement.To address this gap, we introduce BloomBench, part of the Almieyar benchmarking series, the first cognitively human-grounded, bilingual (English–Arabic) multimodal benchmark for VLMs. Grounded in Bloom’s Taxonomy, BloomBench systematically evaluates six levels of cognition (Remember, Understand, Apply, Analyze, Evaluate, Create) through carefully designed image–question–answer tasks. Built with a semi-automated pipeline and validated through a stratified hybrid quality assurance protocol, it ensures scalability, cultural inclusivity, and linguistic fidelity. Leveraging this framework, we conduct a comprehensive study of state-of-the-art VLMs to diagnose their cognitive profiles. Our analysis reveals a sharp cognitive asymmetry: while state-of-the-art models achieve strong performance ceilings in semantic understanding, they struggle substantially with factual recall and creative synthesis. This demonstrates that current general multimodal proficiency masks deeper limitations in specific cognitive layers.Furthermore, our study highlights a critical performance gap between Arabic and English, exposing limitations in current cross-lingual multimodal reasoning. These findings establish a foundation for developing more cognitively aligned and inclusive VLMs.The benchmark framework and dataset is available at: https://github.com/qcri/Almieyar-Oryx-BloomBench.

ACL 2026

ODASim: Ordered, Distinctive and Absolute Semantic Similarity for Code Explanation Evaluation

Prince Kumar, Vitobha Munigala, Jaydeep Sen, Ashish Mittal, Vishwajeet Kumar, Srikanth G. Tamilselvam

Code explanations are increasingly generated by large language models and used in software engineering workflows, making reliable evaluation essential. However, existing model-based and embedding-based methods often fail to distinguish correct explanations from partially or fully incorrect ones, and their similarity scores are poorly calibrated and do not reflect meaningful differences in explanation quality. To address this, we propose ODASim(Orderly, Dstinctive, and Absolute Similarity), a model-agnostic graded fine-tuning framework for embedding models that learns calibrated similarity representations between code and explanations. To support fine-grained supervision and evaluation, we also introduce ODA-X, a novel benchmark for code-to-explanation quality grading, comprising code–explanation pairs graded similarity labels derived from strategic perturbations of gold explanations. We apply our ODASim approach to multiple embedding models and evaluate it on two benchmarks: widely popular CodeXGLUE and our proposed benchmark ODA-X, spanning four programming languages - Python, Java, JavaScript, and Go. Results show that our method achieves up to 35% improvement in F1 score and 85% reduction in Expected Calibration Error (ECE), enabling reliable evaluation of code to explanation quality.

ACL 2026

Datasets for Scientific Literature Understanding: A Survey

Yuanzhe Zhang, Xun Zhao, Maodi Hu, Xi Sun, Donghuan Song, Zhixiong Zhang

Empowering machines to understand scientific literature is crucial for accelerating scientific discovery and advancing the AI for Science (AI4S) paradigm. In this paper, we present a comprehensive survey of datasets serving this domain. We propose a systematic taxonomy that organizes resources spanning structural understanding, text understanding, multimodal understanding and pre-training/instruction fine-tuning. Beyond a structured overview, we discuss the evolution of the field, elucidating how the emergence of Large Language Models (LLMs) has reshaped research priorities of dataset construction. By synthesizing existing datasets and identifying critical future directions, this work provides a roadmap for advancing intelligent scientific research systems.

ACL 2026

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs

Xiaozhe Li, Xinyu Fang, Shengyuan Ding, Yang Li, Linyang Li, Haodong Duan, Qingwen Liu, Kai Chen

Large Language Models (LLMs) have achieved remarkable success on reasoning benchmarks through Reinforcement Learning with Verifiable Rewards (RLVR), excelling at tasks such as math, coding, logic and puzzles. However, existing benchmarks evaluate only correctness, overlooking optimality—the ability to find the best solutions under constraints. We propose , the first comprehensive framework for training and evaluating LLMs on NP-hard optimization problems through quality-aware RLVR. provides three key components: a scalable training infrastructure with instance generators, quality verifiers, and optimal baselines across 10 tasks; a rigorous benchmark with 1,000 instances evaluating both feasibility (Success Rate) and quality (Quality Ratio); and quality-aware rewards enabling continuous improvement beyond binary correctness. Training on Qwen2.5-7B-Instruct-1M with 15K examples achieves 93.1% SR and 46.6% QR, significantly outperforming GPT-4o (29.6% SR, 14.6% QR). Beyond optimization, training on transfers to diverse tasks: mathematics (+2.2%), logic (+1.2%), knowledge (+4.1%), and instruction-following (+6.1%). Our analysis reveals quality-aware rewards improve solutions by 28.8% over binary rewards, and task diversity drives generalization more than data quantity—offering insights into RLVR scaling for complex reasoning.

Keep browsing

More papers from top AI conferences

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