论文检索

Jinwook Park, Kangil Kim

Unsupervised neural grammar induction aims to learn interpretable hierarchical structures from language data. However, existing models face an expressiveness bottleneck, often resulting in unnecessarily large yet underperforming grammars. We identify a core issue, *probability distribution collapse*, as the underlying cause of this limitation. We analyze when and how the collapse emerges across key components of neural parameterization and introduce a targeted solution, *collapse-relaxing neural parameterization*, to mitigate it. Our approach substantially improves parsing performance while enabling the use of significantly more compact grammars across a wide range of languages, as demonstrated through extensive empirical analysis.

Siddhant Bikram Shah, Kristina T. Johnson

Nonverbal vocalizations are an essential component of human communication, conveying rich information without linguistic content. However, their computational analysis is hindered by a lack of lexical anchors in the data, compounded by biased and imbalanced data distributions. While disentangled representation learning has shown promise in isolating specific speech features, its application to nonverbal vocalizations remains unexplored. In this paper, we introduce N-CORE, a novel backbone-agnostic framework designed to disentangle intertwined features like emotion and speaker information from nonverbal vocalizations by leveraging N views of audio samples to learn invariance to specific transformations. N-CORE achieves competitive performance compared to state-of-the-art methods for emotion and speaker classification on the VIVAE, ReCANVo, and ReCANVo-Balanced datasets. We further propose an emotion perturbation function that disrupts affective information while preserving speaker information in audio signals for emotion-invariant speaker classification. Our work informs research directions on paralinguistic speech processing, including clinical diagnoses of atypical speech and longitudinal analysis of communicative development. Our code is available at https://github.com/SiddhantBikram/N-CORE.

John Salvador, Naman Bansal, Mousumi Akter, Souvika Sarkar, Anupam Das, Santu Karmaker

Semantic Overlap Summarization (SOS) is a multi-document summarization task focused on extracting the common information shared cross alternative narratives which is a capability that is critical for trustworthy generation in domains such as news, law, and healthcare. We benchmark popular Large Language Models (LLMs) on SOS and introduce PrivacyPolicyPairs (3P), a new dataset of 135 high-quality samples from privacy policy documents, which complements existing resources and broadens domain coverage. Using the TELeR prompting taxonomy, we evaluate nearly one million LLM-generated summaries across two SOS datasets and conduct human evaluation on a curated subset. Our analysis reveals strong prompt sensitivity, identifies which automatic metrics align most closely with human judgments, and provides new baselines for future SOS research

Shengjie Li, Vincent Ng

While virtually all existing work on Automated Essay Scoring (AES) models an essay as a word sequence, we put forward the novel view that an essay can be modeled as a graph and subsequently propose GAT-AES, a graph-attention network approach to AES. GAT-AES models the interactions among essay traits in a principled manner by (1) representing each essay trait as a trait node in the graph and connecting each pair of trait nodes with directed edges, and (2) allowing neighboring nodes to influence each other by using a convolutional operator to update node representations. Unlike competing approaches, which can only model one-hop dependencies, GAT-AES allows us to easily model multi-hop dependencies. Experimental results demonstrate that GAT-AES achieves the best multi-trait scoring results to date on the ASAP++ dataset. Further analysis shows that GAT-AES outperforms not only alternative graph neural networks but also approaches that use trait-attention mechanisms to model trait dependencies.

Jiazheng Liu, Sipeng Zheng, Börje F. Karlsson, Zongqing Lu

Multimodal large language models (MLLMs), built on large-scale pre-trained vision towers and language models, have shown great capabilities in multimodal understanding. However, most existing MLLMs are trained on single-turn vision question-answering tasks, which do not accurately reflect real-world human conversations. In this paper, we introduce MMDiag, a new large-scale multi-turn multimodal dialogue dataset. This dataset is collaboratively generated through deliberately designed rules and GPT assistance, featuring complex dialogues with contextual dependencies that force models to track, ground, and recall information across multiple turns and disparate visual regions. MMDiag serves as a strong benchmark for multi-turn multimodal dialogue learning and brings more challenges to the grounding and reasoning capabilities of MLLMs. Further, inspired by human vision processing we present DiagNote, equipped with multimodal grounding and reasoning capabilities. DiagNote adopts a novel dual-module architecture that explicitly separates reasoning from grounding: a reasoning module (Deliberate) performs step-by-step Chain-of-Thought, while a grounding module (Gaze) provides precise visual focus by predicting bounding box annotations. These modules interact iteratively, enabling DiagNote to dynamically refine its understanding. We empirically demonstrate the advantages of DiagNote in both grounding and jointly processing and reasoning with vision and language information over existing MLLMs.

Wenyuan Zhang, Shuaiyi Nie, Jiawei Sheng, Zefeng Zhang, Xinghua Zhang, Yongquan He, Tingwen Liu

Large language model (LLM) role-playing has gained widespread attention. Authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs’ ability to detect characters’ known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose RoleKE-Bench to evaluate LLMs’ ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to detect these two types of errors effectively, especially when it comes to familiar knowledge. We experimented with various reasoning strategies and propose an agent-based reasoning method, Self-Recollection and Self-Doubt (S^2RD), to explore further the potential for improving error detection capabilities.

Yue Fan, Handong Zhao, Ruiyi Zhang, Yu Shen, Xin Eric Wang, Gang Wu

Graphical User Interface (GUI) action grounding, mapping language instructions to actionable elements on GUI screens, is important for assisting users in interactive tutorials, task automation, accessibility support, etc. Most recent works of GUI action grounding use large GUI datasets to fine-tune Multimodal Large Language Models (MLLMs). However, the fine-tuning data is inherently limited to specific GUI environments, leading to significant performance degradation in novel environments due to the generalization challenges in the GUI domain. Therefore, we argue that GUI action grounding models should be further aligned with novel environments before deployment to optimize their performance. To address this, we first propose GUI-Bee, an MLLM-based autonomous agent, to collect high-quality, environment-specific data through exploration and then continuously fine-tune GUI grounding models with the collected data. To ensure the GUI action grounding models generalize to various screens within the target novel environment after the continuous fine-tuning, we equip GUI-Bee with a novel Q-value-Incentive In-Context Reinforcement Learning (Q-ICRL) algorithm that optimizes exploration efficiency and exploration data quality. In the experiment, we introduce NovelScreenSpot to test how well the data can help align GUI action grounding models to novel environments. Furthermore, we conduct an ablation study to validate the Q-ICRL method in enhancing the efficiency of GUI-Bee.

Ziyu Chen, Junfei Sun, Chenxi Li, Tuan Dung Nguyen, Jing Yao, Xiaoyuan Yi, Xing Xie, Chenhao Tan, Lexing Xie

Identifying human morals and values embedded in language is essential to empirical studies of communication. However, researchers often face substantial difficulty navigating the diversity of theoretical frameworks and data available for their analysis. Here, we contribute MoVa, a well-documented suite of resources for generalizable classification of human morals and values, consisting of (1) 16 labeled datasets and benchmarking results from four theoretically-grounded frameworks; (2) a lightweight LLM prompting strategy that outperforms fine-tuned models across multiple domains and frameworks; and (3) a new application that helps evaluate psychological surveys. In practice, we specifically recommend a classification strategy, all@once, that scores all related concepts simultaneously, resembling the well-known multi-label classifier chain. The data and methods in MoVa can facilitate many fine-grained interpretations of human and machine communication, with potential implications for the alignment of machine behavior.

Lisa Alazraki, Maximilian Mozes, Jon Ander Campos, Tan Yi-Chern, Marek Rei, Max Bartolo

Showing incorrect answers to Large Language Models (LLMs) is a popular strategy to improve their performance in reasoning-intensive tasks. It is widely assumed that, in order to be helpful, the incorrect answers must be accompanied by comprehensive rationales, explicitly detailing where the mistakes are and how to correct them. However, in this work we present a counterintuitive finding: we observe that LLMs perform *better* in math reasoning tasks when these rationales are eliminated from the context and models are left to infer on their own what makes an incorrect answer flawed. This approach also substantially outperforms chain-of-thought prompting in our evaluations. These results are consistent across LLMs of different sizes and varying reasoning abilities. To gain an understanding of *why* LLMs learn from mistakes more effectively without explicit corrective rationales, we perform a thorough analysis, investigating changes in context length and answer diversity between different prompting strategies, and their effect on performance. We also examine evidence of overfitting to the in-context rationales when these are provided, and study the extent to which LLMs are able to autonomously infer high-quality corrective rationales given only incorrect answers as input. We find evidence that, while incorrect answers are more beneficial for LLM learning than additional diverse *correct* answers, explicit corrective rationales over-constrain the model, thus limiting those benefits.

Zeinab Sadat Taghavi, Ali Modarressi, Yunpu Ma, Hinrich Schuetze

Retrieval systems are central to many NLP pipelines, but often rely on surface-level cues such as keyword overlap and lexical semantic similarity. To evaluate retrieval beyond these shallow signals, recent benchmarks introduce reasoning-heavy queries; however, they primarily shift the burden to query-side processing techniques – like prompting or multi-hop retrieval – that can help resolve complexity. In contrast, we present Impliret, a benchmark that shifts the reasoning challenge to document-side processing: The queries are simple, but relevance depends on facts stated implicitly in documents through temporal (e.g., resolving “two days ago”), arithmetic, and world knowledge relationships. We evaluate a range of sparse and dense retrievers, all of which struggle in this setting: the best nDCG@10 is only 14.91%. We also test whether long-context models can overcome this limitation. But even with a short context of only thirty documents, including the positive document, GPT-o4-mini scores only 55.54%, showing that document-side reasoning remains a challenge. Our codes are available at github.com/ZeinabTaghavi/IMPLIRET.

Chenglong Lu, Chenxiao Li, Jingwei Cheng, Yongquan Ji, Guoqing Chen, Fu Zhang

Multi-modal entity alignment (MMEA) aims to identify equivalent entities between two multimodal knowledge graphs (MMKGs). However, the intrinsic noise within modalities, such as the inconsistency in visual modality and redundant attributes, has not been thoroughly investigated. Excessive noise not only weakens semantic representation but also increases the risk of overfitting in attention-based fusion methods. To address this, we propose LGEA, a novel LLMguided MMEA framework that prioritizes noise reduction before fusion. Specifically, LGEA introduces two key strategies: (1) fine-grained visual filtering to remove irrelevant images at the semantic level, and (2) contextual summarization of attribute information to enhance entity semantics. To our knowledge, we are the first work to apply LLMs for both visual filtering and attribute-level semantic enhancement in MMEA. Experiments on multiple benchmarks, including the noisy FB YG dataset, show that LGEA sets a new state-of-the-art (SOTA) in robust multi-modal alignment, highlighting the potential of noise-aware strategies as a promising direction for future MMEA research.

Rana Salama, Jason Cai, Michelle Yuan, Anna Currey, Monica Sunkara, Yi Zhang, Yassine Benajiba

Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools. A key capability is the integration of long-term memory capabilities, enabling these agents to draw upon historical interactions and knowledge. However, the growing memory size and need for semantic structuring pose significant challenges. In this work, we propose an autonomous memory augmentation approach, MemInsight, to enhance semantic data representation and retrieval mechanisms. By leveraging autonomous augmentation to historical interactions, LLM agents are shown to deliver more accurate and contextualized responses. We empirically validate the efficacy of our proposed approach in three task scenarios; conversational recommendation, question answering and event summarization. On the LLM-REDIAL dataset, MemInsight boosts persuasiveness of recommendations by up to 14%. Moreover, it outperforms a RAG baseline by 34% in recall for LoCoMo retrieval. Our empirical results show the potential of MemInsight to enhance the contextual performance of LLM agents across multiple tasks.

Beiduo Chen, Yang Janet Liu, Anna Korhonen, Barbara Plank

The recent rise of reasoning-tuned Large Language Models (LLMs)—which generate chains of thought (CoTs) before giving the final answer—has attracted significant attention and offers new opportunities for gaining insights into human label variation, which refers to plausible differences in how multiple annotators label the same data instance.Prior work has shown that LLM-generated explanations can help align model predictions with human label distributions, but typically adopt a *reverse* paradigm: producing explanations based on given answers. In contrast, CoTs provide a *forward* reasoning path that may implicitly embed rationales for each answer option, before generating the answers. We thus propose a novel LLM-based pipeline enriched with linguistically-grounded discourse segmenters to extract supporting and opposing statements for each answer option from CoTs with improved accuracy. We also propose a rank-based HLV evaluation framework that prioritizes the ranking of answers over exact scores, which instead favor direct comparison of label distributions.Our method outperforms a direct generation method as well as baselines on three datasets, and shows better alignment of ranking methods with humans, highlighting the effectiveness of our approach.

Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang 等

Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks. However, prompt engineering remains an impediment for end users due to rapid advances in models, tasks, and associated best practices. To mitigate this, Automatic Prompt Optimization (APO) techniques have recently emerged that use various automated techniques to help improve the performance of LLMs on various tasks. In this paper, we present a comprehensive survey summarizing the current progress and remaining challenges in this field. We provide a formal definition of APO, a 5-part unifying framework, and then proceed to rigorously categorize all relevant works based on their salient features therein. We hope to spur further research guided by our framework.

Yumeng Wang, Xiuying Chen, Suzan Verberne

In exploratory search, users often submit vague queries to investigate unfamiliar topics, but receive limited feedback about how the search engine understood their input. This leads to a self-reinforcing cycle of mismatched results and trial-and-error reformulation. To address this, we study the task of generating user-facing natural language query intent descriptions that surface what the system likely inferred the query to mean, based on post-retrieval evidence. We propose QUIDS, a method that leverages dual-space contrastive learning to isolate intent-relevant information while suppressing irrelevant content. QUIDS combines a dual-encoder representation space with a disentangling decoder that works together to produce concise and accurate intent descriptions. Enhanced by intent-driven hard negative sampling, the model significantly outperforms state-of-the-art baselines across ROUGE, BERTScore, and human/LLM evaluations. Our qualitative analysis confirms QUIDS’ effectiveness in generating accurate intent descriptions for exploratory search. Our work contributes to improving the interaction between users and search engines by providing feedback to the user in exploratory search settings.

Alhanoof Althnian, Norah A. Alzahrani, Shaykhah Z. Alsubaie, Eman Albilali, Ahmed Abdelali, Nouf M. Alotaibi, M Saiful Bari, Yazeed Alnumay, Abdulhamed Alothaimen, Maryam Saif 等

The rapid advancements of Large Language models (LLMs) necessitate robust benchmarks. In this paper, we present AraEval, a pioneering and comprehensive evaluation suite specifically developed to assess the advanced knowledge, reasoning, truthfulness, and instruction- following capabilities of foundation models in the Arabic context. AraEval includes a diverse set of evaluation tasks that test various dimensions of knowledge and reasoning, with a total of 24,378 samples. These tasks cover areas such as linguistic understanding, factual recall, logical inference, commonsense reasoning, mathematical problem-solving, and domain-specific expertise, ensuring that the evaluation goes beyond basic language comprehension. It covers multiple domains of knowledge, such as science, history, religion, and literature, ensuring that the LLMs are tested on a broad spectrum of topics relevant to Arabic-speaking contexts. AraEval is designed to facilitate comparisons across different foundation models, enabling LLM developers and users to benchmark perfor- mance effectively. In addition, it provides diagnostic insights to identify specific areas where models excel or struggle, guiding further development. AraEval datasets can be found at https://huggingface.co/collections/humain-ai/araeval-datasets-687760e04b12a7afb429a4a0.

Andong Chen, Lianzhang Lou, Kehai Chen, Xuefeng Bai, Yang Xiang, Muyun Yang, Tiejun Zhao, Min Zhang

Large language models (LLMs) have shown remarkable performance in general translation tasks. However, the increasing demand for high-quality translations that are not only adequate but also fluent and elegant. To assess the extent to which current LLMs can meet these demands, we introduce a suitable benchmark (PoetMT) for translating classical Chinese poetry into English. This task requires not only adequacy in translating culturally and historically significant content but also a strict adherence to linguistic fluency and poetic elegance. Our study reveals that existing LLMs fall short of this task. To address these issues, we propose RAT, a Retrieval-Augmented machine Translation method that enhances the translation process by incorporating knowledge related to classical poetry. Additionally, we propose an automatic evaluation metric based on GPT-4, which better assesses translation quality in terms of adequacy, fluency, and elegance, overcoming the limitations of traditional metrics.

Jio Choi, Mohit Bansal, Elias Stengel-Eskin

Studying the responses of large language models (LLMs) to loopholes presents a two-fold opportunity. First, it affords us a lens through which to examine ambiguity and pragmatics in LLMs, since exploiting a loophole requires identifying ambiguity and performing sophisticated pragmatic reasoning. Second, loopholes pose an interesting and novel alignment problem where the model is presented with conflicting goals and can exploit ambiguities to its own advantage. To address these questions, we design scenarios where LLMs are given a goal and an ambiguous user instruction in conflict with the goal, with scenarios covering scalar implicature, structural ambiguities, and power dynamics. We then measure different models’ abilities to exploit loopholes to satisfy their given goals as opposed to the goals of the user. We find that both closed-source and stronger open-source models can identify ambiguities and exploit their resulting loopholes, presenting a potential AI safety risk. Our analysis indicates that models which exploit loopholes explicitly identify and reason about both ambiguity and conflicting goals.

Liuxuan Jiao, Chen Gao, Yiqian Yang, Chenliang Zhou, YiXian Huang, Xinlei Chen, Yong Li

We present a statistical framework for modeling and controlling large language model (LLM) response lengths using extreme value theory. Analyzing 14,301 GPT-4o responses across temperature and prompting conditions, with cross-validation on Qwen and DeepSeek architectures, we demonstrate that verbosity follows Weibull-type generalized extreme value (GEV) distributions with heavier tails under stochastic generation. Our key contributions include: (1) development of a novel GEV-generalized Pareto (GPD) hybrid model that improves tail fit (R^2_{\text{CDF}}=0.9993 vs standalone GEV’s 0.998) while maintaining architectural generalizability; (2) quantitative characterization of prompt anchoring effects across models, showing reduced dispersion but increased outliers under randomization; and (3) identification of temperature-dependent response patterns that persist across architectures, with higher temperatures amplifying length variability while preserving extreme-value mechanisms. The hybrid model’s threshold selection method enables precise verbosity control in production systems regardless of model choice. While validated on multiple architectures, generalizability to emerging model families requires further study.

Finlay Fehlauer, Kyle Mahowald, Tiago Pimentel

In this paper, we investigate the convergence of language models (LMs) trained under different random seeds, measuring convergence as the expected per-token Kullback–Leibler (KL) divergence across seeds. By comparing LM convergence as a function of model size and training checkpoint, we identify a four-phase convergence pattern: (i) an initial \textbf{uniform phase}, (ii) a \textbf{sharp-convergence phase}, (iii) a \textbf{sharp-divergence phase}, and (iv) a \textbf{slow-reconvergence phase}. Further, we observe that larger models reconverge faster in later training stages, while smaller models never actually reconverge; these results suggest that a certain model size may be necessary to learn stable distributions. Restricting our analysis to specific token frequencies, or part-of-speech (PoS) tags further reveals that convergence is uneven across linguistic categories: frequent tokens and function words converge faster and more reliably than their counterparts (infrequent tokens and content words). Overall, our findings highlight factors that influence the stability of the learned distributions in model training.