论文检索

Jikun Hu, Dongsheng Guo, Yuli Liu, Qingyao Ai, Lixuan Wang, Xuebing Sun, Qilei Zhang, Quan Zhou, Cheng Luo

Long-context extension seeks to expand the contextual window in pre-trained large language models (LLMs), allowing them to handle several multiples of their original training context lengths. The primary method for extending the window length involves expanding the initial positional encodings, such as interpolating and extrapolation new positions based on Rotary Position Embedding (RoPE). This expansion inevitably disrupts the positional encodings learned during pre-training, thereby affecting the attention allotment and introducing unseen positional encoding distributions. To address this issue, we propose a new extension strategy based on RoPE, namely Periodic Extrapolation Positional Encodings (PEPE). This strategy expands pre-trained high dimensional components of positional encodings by replicating them in a periodic manner, thereby neither altering the learned positional encoding spaces nor introducing new positional encoding distributions. Experiments demonstrate that PEPE-based approaches can significantly improve long-context extension capabilities using just one-fourth the fine-tuning steps required by state-of-the-art methods. In addition, we analyze the characteristics of PEPE based methods and the key parameters that contribute to their effectiveness. The code is publicly available.

Batu El, Mert Yuksekgonul, James Zou

Recent works began to automate the design of agentic systems using meta-agents that propose and iteratively refine new agent architectures. In this paper, we examine three key challenges in a common class of meta-agents. First, we investigate how a meta-agent learns across iterations and find that simply expanding the context with all previous agents, as proposed by previous works, performs worse than ignoring prior designs entirely. We show that the performance improves with an evolutionary approach. Second, although the meta-agent designs multiple agents during training, it typically commits to a single agent at test time. We find that the designed agents have low behavioral diversity, limiting the potential for their complementary use. Third, we assess when automated design is economically viable. We find that only in a few cases—specifically, two datasets—the overall cost of designing and deploying the agents is lower than that of human-designed agents when deployed on over 15,000 examples. In contrast, the performance gains for other datasets do not justify the design cost, regardless of scale.

Abhinay Shankar Belde, Rohit Ramkumar, Jonathan Rusert

Adversarial text attack research plays a crucial role in evaluating the robustness of NLP models. However, the increasing complexity of transformer-based architectures has dramatically raised the computational cost of attack testing, especially for researchers with limited resources (e.g., GPUs). Existing popular black-box attack methods often require a large number of queries, which can make them inefficient and impractical for researchers. To address these challenges, we propose two new attack selection strategies called Hybrid and Dynamic Select, which better combine the strengths of previous selection algorithms. Hybrid Select merges generalized BinarySelect techniques with GreedySelect by introducing a size threshold to decide which selection algorithm to use. Dynamic Select provides an alternative approach of combining the generalized Binary and GreedySelect by learning which lengths of texts each selection method should be applied to. This greatly reduces the number of queries needed while maintaining attack effectiveness (a limitation of BinarySelect). Across 4 datasets and 6 target models, our best method(sentence-level Hybrid Select) is able to reduce the number of required queries per attack up 25.82% on average against both encoder models and LLMs, without losing the effectiveness of the attack.

Jinhee Jang, Ayoung Moon, Minkyoung Jung, YoungBin Kim, Seung Jin Lee

The emergence of large language models (LLMs) has brought a new paradigm to automated essay scoring (AES), a long-standing and practical application of natural language processing in education. However, achieving human-level multi-perspective understanding and judgment remains a challenge. In this work, we propose Roundtable Essay Scoring (RES), a multi-agent evaluation framework designed to perform precise and human-aligned scoring under a zero-shot setting. RES constructs evaluator agents based on LLMs, each tailored to a specific prompt and topic context. Each agent independently generates a trait-based rubric and conducts a multi-perspective evaluation. Then, by simulating a roundtable-style discussion, RES consolidates individual evaluations through a dialectical reasoning process to produce a final holistic score that more closely aligns with human evaluation. By enabling collaboration and consensus among agents with diverse evaluation perspectives, RES outperforms prior zero-shot AES approaches. Experiments on the ASAP dataset using ChatGPT and Claude show that RES achieves up to a 34.86% improvement in average QWK over straightforward prompting (Vanilla) methods.

Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski, Evangelos Eleftheriou, Martino Dazzi

One challenge of quantizing a large language model (LLM) is the presence of outliers. Outliers often make uniform quantization schemes less effective, particularly in extreme cases such as 4-bit quantization. We introduce KurTail, a new post-training quantization (PTQ) scheme that leverages Kurtosis-based rotation to mitigate outliers in the activations of LLMs. Our method optimizes Kurtosis as a measure of tailedness. This approach enables the quantization of weights, activations, and the KV cache in 4 bits. We utilize layer-wise optimization, ensuring memory efficiency. KurTail outperforms existing quantization methods, offering a 13.3% boost in MMLU accuracy and a 15.5% boost in Wiki perplexity compared to QuaRot. It also outperforms SpinQuant with a 2.6% MMLU gain and reduces perplexity by 2.9%, all while reducing the training cost. For comparison, learning the rotation using SpinQuant for Llama3-70B requires at least four NVIDIA H100 80GB GPUs, whereas our method requires only a single GPU, making it more accessible.

Hanqing Li, Sharika Mahadevan, Kiran Jyothi Sheena, Henry Liang, Diego Klabjan

We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a wide range of graph reasoning tasks. In GRRAF, the target graph is stored in a graph database, and the LLM is prompted to generate executable code queries that retrieve the necessary information. This approach circumvents the limitations of existing methods that require extensive finetuning or depend on predefined algorithms, and it incorporates an error feedback loop with a time-out mechanism to ensure both correctness and efficiency. Experimental evaluations on the GraphInstruct dataset reveal that GRRAF achieves 100% accuracy on most graph reasoning tasks, including cycle detection, bipartite graph checks, shortest path computation, and maximum flow, while maintaining consistent token costs regardless of graph sizes. Imperfect but still very high performance is observed on subgraph matching. Notably, GRRAF scales effectively to large graphs with up to 10,000 nodes.

Valentin Barriere, Nahuel Gomez, Léo Hemamou, Sofia Callejas, Brian Ravenet

Aiming towards improving current computational models of humor detection, we propose a new multimodal dataset of stand-up comedies, in seven languages: English, French, Spanish, Italian, Portuguese, Hungarian and Czech. Our dataset of more than 330 hours %, is at the time of writing the biggest available for this type of task, and the most diverse. The whole dataset is automatically annotated in laughter (from the audience), and the subpart left for model validation is manually annotated.% Contrary to contemporary approaches, we do not frame the task of humor detection as a binary sequence classification, but as word-level sequence labeling, in order to take into account all the context of the sequence and to capture the continuous joke tagging mechanism typically occurring in natural conversations. As par with unimodal baselines results, we propose a method for e propose a method to enhance the automatic laughter detection based on Audio Speech Recognition errors. Our code and data are available online: https://tinyurl.com/EMNLPHumourStandUpAnonym

Jingen Qu, Lijun Li, Bo Zhang, Yichen Yan, Jing Shao

Multimodal large language models (MLLMs) are rapidly evolving, presenting increasingly complex safety challenges. However, current dataset construction methods, which are risk-oriented, fail to cover the growing complexity of real-world multimodal safety scenarios (RMS). And due to the lack of a unified evaluation metric, their overall effectiveness remains unproven. This paper introduces a novel image-oriented self-adaptive dataset construction method for RMS, which starts with images and end constructing paired text and guidance responses. Using the image-oriented method, we automatically generate an RMS dataset comprising 35,610 image–text pairs with guidance responses. Additionally, we introduce a standardized safety dataset evaluation metric: fine-tuning a safety judge model and evaluating its capabilities on other safety datasets. Extensive experiments on various tasks demonstrate the effectiveness of the proposed image-oriented pipeline. The results confirm the scalability and effectiveness of the image-oriented approach, offering a new perspective for the construction of real-world multimodal safety datasets.

Yitao Long, Tiansheng Hu, Yilun Zhao, Arman Cohan, Chen Zhao

Large Language Models (LLMs) frequently hallucinate to long-form questions, producing plausible yet factually incorrect answers. A common mitigation strategy is to provide attribution to LLM outputs. However, existing benchmarks primarily focus on simple attribution that retrieves supporting textual evidence as references. We argue that in real-world scenarios such as financial applications, attribution goes beyond reference retrieval.We introduce FinLFQA, a benchmark designed to evaluate the ability of LLMs to generate long-form answers to complex financial questions with reliable and nuanced attributions. FinLFQA evaluates three critical aspects of attribution through human annotations: (1) supporting evidence extracted from financial reports, (2) intermediate numerical reasoning steps, and (3) domain-specific financial knowledge that informs the reasoning process.We further provide an automatic evaluation framework covering both answer quality and attribution quality. Through extensive experiments on eight LLMs across multiple attribution-generation paradigms, we find that fine-grained metrics are important to distinguish model capabilities, that end-to-end generation achieves comparable performance to post-hoc approaches, and that iterative refinement only helps when guided by external feedback.

Kuan Lok Zhou, Jiayi Chen, Siddharth Suresh, Reuben Narad, Timothy T. Rogers, Lalit K Jain, Robert D Nowak, Bob Mankoff, Jifan Zhang

Large Language Models (LLMs) have shown significant limitations in understanding creative content, as demonstrated by Hessel et al. (2023)’s influential work on the New Yorker Cartoon Caption Contest (NYCCC). Their study exposed a substantial gap between LLMs and humans in humor comprehension, establishing that understanding and evaluating creative content is key challenge in AI development. We revisit this challenge by decomposing humor understanding into three components and systematically improve each: enhancing visual understanding through improved annotation, utilizing LLM-generated humor reasoning and explanations, and implementing targeted alignment with human preference data. Our refined approach achieves 82.4% accuracy in caption ranking, significantly improving upon the previous 67% benchmark and matching the performance of world-renowned human experts in this domain. Notably, while attempts to mimic subgroup preferences through various persona prompts showed minimal impact, model finetuning with crowd preferences proved remarkably effective. These findings reveal that LLM limitations in creative judgment can be effectively addressed through focused alignment to specific subgroups and individuals. Lastly, we propose the position that achieving artificial general intelligence necessitates systematic collection of human preference data across creative domains. We advocate that just as human creativity is deeply influenced by individual and cultural preferences, training LLMs with diverse human preference data may be essential for developing true creative understanding.

Huu Tuong Tu, Huan Vu, Cuong Tien Nguyen, Dien Hy Ngo, Nguyen Thi Thu Trang

Traditional voice conversion (VC) methods typically attempt to separate speaker identity and linguistic information into distinct representations, which are then combined to reconstruct the audio. However, effectively disentangling these factors remains challenging, often leading to information loss during training. In this paper, we propose a new approach that leverages synthetic speech data generated by a high-quality, pretrained multispeaker text-to-speech (TTS) model. Specifically, synthetic data pairs that share the same linguistic content but differ in speaker identity are used as input-output pairs to train the voice conversion model. This enables the model to learn a direct mapping between source and target voices, effectively capturing speaker-specific characteristics while preserving linguistic content. Additionally, we introduce a flexible training strategy for any-to-any voice conversion that generalizes well to unseen speakers and new languages, enhancing adaptability and performance in zero-shot scenarios. Our experiments show that our proposed method achieves a 16.35% relative reduction in word error rate and a 5.91% improvement in speaker cosine similarity, outperforming several state-of-the-art methods. Voice conversion samples can be accessed at: https://oovc-emnlp-2025.github.io/

Chimaobi Okite, Naihao Deng, Kiran Bodipati, Huaidian Hou, Joyce Chai, Rada Mihalcea

Recent years have witnessed a growing interest in personalizing the responses of large language models (LLMs). While existing evaluations primarily focus on whether a response aligns with a user’s preferences, we argue that factuality is an equally important yet often overlooked dimension. In the context of personalization, we define a model as robust if its responses are both factually accurate and align with the user preferences. To assess this, we introduce PERG, a scalable framework for evaluating robustness of LLMs in personalization, along with a new dataset, PERGData. We evaluate fourteen models from five different model families using different prompting methods. Our findings show that current LLMs struggle with robust personalization: even the strongest models (GPT-4.1, LLaMA3-70B) fails to maintain correctness in 5% of previously successful cases without personalization, while smaller models (e.g., 7B scale) can fail more than 20% of the time. Further analysis reveals that robustness is significantly affected by the nature of the query and the type of user preference. To mitigate these failures, we propose Pref-Aligner, a two-stage approach that improves robustness by an average of 25% across models. Our work highlights critical gaps in current evaluation practices and introduces tools and metrics to support more reliable, user-aligned LLM deployments.

Fu Zhang, Panfeng Zhang, Jingwei Cheng

Temporal knowledge graph (TKG) extrapolation aims to predict future facts by modeling the dynamic evolution of historical facts within TKGs. Existing methods often neglect the complex semantic relationships between relations when modeling their dynamic evolution, leading to incomplete relation representations and affecting the accuracy of reasoning. Inspired by the advancements in large language models (LLMs), we propose Semantic Relationship Mining based on LLMs (SRM-LLM), a novel approach for extracting semantic relationships to achieve TKG extrapolation. By leveraging LLMs to analyze the types of relations, we first identify several common relation types (e.g., causal, synonymous) in TKGs. We then design the LLM-based prompting strategy to capture latent semantic connections between relations, enabling the construction of relational association subgraphs for relation representation learning. In addition, SRM-LLM further enhances reasoning capabilities by incorporating structured logical constraints to guide inference. Experiments on five TKG datasets show significant performance gains and achieve new state of the art (SOTA) results, confirming the effectiveness of our method on TKG extrapolation tasks.

Jiashi Lin, Changhong Jiang, Yixiao Wang, Xinyi Zhu, Zhongtian Hu, Wei Zhang

Knowledge Graph Embedding (KGE) seeks to learn latent representations of entities and relations to support knowledge-driven AI systems. However, existing KGE approaches often exhibit a growing discrepancy between the learned embedding space and the intrinsic structural semantics of the underlying knowledge graph. This divergence primarily stems from the over-reliance on geometric criteria for assessing triple plausibility, whose effectiveness is inherently limited by the sparsity of factual triples and the disregard of higher-order structural dependencies in the knowledge graph. To overcome this limitation, we introduce Structure-aware Calibration (SaCa), a versatile framework designed to calibrate KGEs through the integration of global structural patterns. SaCa designs two new components: (i) Structural Proximity Measurement, which captures multi-order structural signals from both entity and entity-relation perspectives; and (ii) KG-Induced Soft-weighted Contrastive Learning (KISCL), which assigns soft weights to hard-to-distinguish positive and negative pairs, enabling the model to better reflect nuanced structural dependencies. Extensive experiments on seven benchmarks demonstrate that SaCa consistently boosts performance across ten KGE models on link prediction and entity classification tasks with minimal overhead.

Weicheng Ma, Hefan Zhang, Shiyu Ji, Farnoosh Hashemi, Qichao Wang, Ivory Yang, Joice Chen, Juanwen Pan, Michael Macy, Saeed Hassanpour 等

Large language models (LLMs) have been used to synthesize persuasive dialogues for studying persuasive behavior. However, existing approaches often suffer from issues such as stance oscillation and low informativeness. To address these challenges, we propose reinforced instructional prompting, a method that ensures speaker characteristics consistently guide all stages of dialogue generation. We further introduce multilingual prompting, which aligns language use with speakers’ native languages to better capture cultural nuances. Our experiments involving speakers from eight countries show that continually reinforcing speaker profiles and cultural context improves argument diversity, enhances informativeness, and stabilizes speaker stances. Moreover, our analysis of inter-group versus intra-group persuasion reveals that speakers engaging within their own cultural groups employ more varied persuasive strategies than in cross-cultural interactions. These findings underscore the importance of speaker and cultural awareness in LLM-based persuasion modeling and suggest new directions for developing more personalized, ethically grounded, and culturally adaptive LLM-generated dialogues.

Zhenyi Wang, Yapeng Jia, Haiyan Ning, Peng Wang, Dan Wang, Yitao Cao

As general large language models continue to advance, their real-world adaptation through effective fine-tuning remains a significant challenge. We introduce Hierarchical Multilevel Contrastive Learning (HMCL), a new contrastive learning framework that improves task-specific text representation for general models. HMCL integrates 3-level semantic differentiation (positive, weak-positive, and negative) and unifies contrastive learning, pair classification, and ranking objectives into a cohesive optimization strategy. HMCL demonstrates exceptional results across multi-domain and multilingual benchmarks, including text similarity, retrieval, reranking and Retrieval-Augmented Generation (RAG) tasks. It outperforms top unsupervised methods and supervised fine-tuning approaches while maintaining broad compatibility with architectures ranging from BERT to Qwen, 330M to 7B. In real-world merchant consultation scenarios, HMCL shows a 0.70-6.24 point improvement over original fine-tuning methods in large-scale base models. This establishes HMCL as a versatile solution that bridges the gap between general-purpose models and specialized industrial applications.

Zitao Wang, Xinyi Wang, Wei Hu

We study continual information extraction (IE), which aims to extract emerging information across diverse IE tasks incessantly while avoiding forgetting. Existing approaches are either task-specialized for a single IE task or suffer from catastrophic forgetting and insufficient knowledge transfer in continual IE. This paper proposes a new continual IE model using token-level mixture of LoRA experts with LLMs. We leverage a LoRA router to route each token to the most relevant LoRA experts, facilitating effective knowledge transfer among IE tasks. We guide task experts’ selection by task keys to retain the IE task-specific knowledge and mitigate catastrophic forgetting. We design a gate reflection method based on knowledge distillation to address forgetting in the LoRA router and task keys. The experimental results show that our model achieves state-of-the-art performance, effectively mitigating catastrophic forgetting and enhancing knowledge transfer in continual IE.

Yunhai Hu, Zining Liu, Zhenyuan Dong, Tianfan Peng, Bradley McDanel, Sai Qian Zhang

Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization approaches like pruning and quantization often compromise model quality, recent advances in generation-refinement frameworks demonstrate that this trade-off can be significantly mitigated.This survey presents a comprehensive taxonomy of generation-refinement frameworks, analyzing methods across autoregressive sequence tasks. We categorize methods based on their generation strategies (from simple n-gram prediction to sophisticated draft models) and refinement mechanisms (including single-pass verification and iterative approaches). Through systematic analysis of both algorithmic innovations and system-level implementations, we examine deployment strategies across computing environments and explore applications spanning text, images, and speech generation. This systematic examination of both theoretical frameworks and practical implementations provides a foundation for future research in efficient autoregressive decoding. In the appendix A, we additionally provide experimental comparisons of various baseline methods.

Yang Wu, Raha Moraffah, Rujing Yao, Jinhong Yu, Zhimin Tao, Xiaozhong Liu

Large Language Models (LLMs) have demonstrated an impressive level of general knowledge. However, they often struggle in highly specialized and sensitive domains such as drug discovery and rare disease research due to the lack of expert knowledge, which is often costly to obtain. In this paper, we propose a novel framework (PU-ADKA) designed to efficiently enhance domain-specific LLMs by actively engaging domain experts within a fixed budget. Unlike traditional fine-tuning approaches, PU-ADKA proactively identifies and queries the most appropriate expert from a team, taking into account each expert’s availability, competency, knowledge boundaries, and consultation cost. We train PU-ADKA using simulations on PubMed publication data and validate it through domain expert interactions, showing promising improvements in LLM domain knowledge acquisition. Furthermore, our experiments with a real-world drug development team validate that PU-ADKA can significantly enhance LLM performance in specialized domains while adhering to strict budget constraints. In addition to outlining our methodological innovations and experimental results, we release a new benchmark dataset, CKAD, for cost-effective LLM domain knowledge acquisition to foster further research in this challenging area.

Jianfeng Pan, Senyou Deng, Shaomang Huang

Research on LLM technologies is rapidly emerging, with most of them employ a ‘fast thinking’ approach to inference. Most LLMs generate the final result based solely on a single query and LLM’s reasoning capabilities. However, with the advent of OpenAI-o1, ‘slow thinking’ techniques have garnered increasing attention because its process is closer to the human thought process. Inspired by the human ability to constantly associate and replenish knowledge during thinking, we developed the novel Chain-of-Associated-Thoughts (CoAT) framework, which introduces an innovative synergy between the Monte Carlo Tree Search (MCTS) algorithm and a dynamic mechanism for integrating new key information, termed ‘associative memory’. By combining the structured exploration capabilities of MCTS with the adaptive learning capacity of associative memory, CoAT significantly expands the LLM search space, enabling our framework to explore diverse reasoning pathways and dynamically update its knowledge base in real-time. This allows the framework to not only revisit and refine earlier inferences but also adaptively incorporate evolving information, ensuring that the final output is both accurate and comprehensive. We validate CoAT’s effectiveness across a variety of generative and reasoning tasks. Quantitative experiments show that CoAT achieves over 10% performance improvement on open-source multi-hop reasoning datasets (HotpotQA, MuSiQue) and more than 15% gain on our proprietary CRB dataset.