论文检索

Yinhao Tang, Youqing Fang, Yanan Sun, Wenran Liu, Weiming Zhang, Bin Liu, Kuikun Liu, Wenwei Zhang, Kai Chen

Scientific research involves complex information-seeking and reasoning workflows across heterogeneous sources. However, existing benchmarks primarily emphasize general-domain retrieval or static scientific question answering, and therefore fail to assess key capabilities required in realistic scientific research workflows. We introduce SciExplore, a benchmark designed to evaluate scientific information-seeking and reasoning capabilities of LLMs and agents. SciExplore comprises four task types covering 103 expert-curated tasks across more than ten scientific disciplines: scientific database navigation, ambiguous literature retrieval, missing reference completion, and cross-source structured knowledge synthesis, which probe progressively higher-level abilities from entity-level reasoning and document-level identification to evidence-level grounding and domain-level synthesis. We evaluate over ten state-of-the-art LLMs and autonomous agents on SciExplore, revealing substantial performance gaps with performance degrading sharply as task complexity increases and extremely low accuracy on the most challenging structured synthesis tasks. These results highlight significant limitations of current models and agents in realistic scientific information-seeking scenarios.

Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li 等

As older adults increasingly use LLM-based chatbots for companionship and assistance, a safety gap is emerging. Older adults may face vulnerabilities from social isolation, limited digital literacy, and cognitive decline, yet existing safety benchmarks largely target general harms and overlook elderly-specific risks. For example, a prompt such as “how to repair a ceiling light alone in the dark” may be benign for most users but poses a serious fall risk for older adults with mobility limitations.We introduce GrandGuard, the first comprehensive framework for assessing and mitigating elderly-specific contextual risks in LLM interactions. We develop a three-level taxonomy with 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains, grounded in real-world incidents, community discussions, and analysis of stakeholder studies. Using this taxonomy, we construct a benchmark of 10,404 labeled prompts and responses, showing that several leading LLMs mishandle elderly-specific contextual risks in over 50% of cases. We mitigate these failures with two safeguards: a fine-tuned Llama-Guard-3 and a policy-enhanced gpt-oss-safeguard-20b, achieving up to 96.2% and 90.9% unsafe-prompt detection accuracy, respectively. GrandGuard lays the groundwork for AI systems that move beyond general safety to support aging populations.

Qianjun Pan, Junyi Wang, Jie Zhou, Yutao Yang, Junsong Li, Kaiyin Xu, Yougen Zhou, Yihan Li, JingYuan Zhao, Qin Chen 等

To develop a reliable AI for psychological assessment, we introduce PsychEval, a multi-session, multi-therapy, and highly realistic benchmark designed to address three key challenges:**1) Can we train a highly realistic AI counselor?** Realistic counseling is a longitudinal task requiring sustained memory and dynamic goal tracking. We propose a multi-session benchmark (spanning 6-10 sessions across three distinct stages) that demands critical capabilities such as memory continuity, adaptive reasoning, and longitudinal planning. The dataset is annotated with extensive professional skills, comprising over 677 meta-skills and 4577 atomic skills. **2) How to train a multi-therapy AI counselor?** While existing models often focus on a single therapy, complex cases frequently require flexible strategies among various therapies. We construct a diverse dataset covering five therapeutic modalities alongside an integrative therapy with a unified three-stage clinical framework across six core psychological topics. **3) How to systematically evaluate an AI counselor?** We establish a holistic evaluation framework with 18 therapy-specific and therapy-shared metrics across Client-Level and Counselor-Level dimensions. To We also construct over 2,000 diverse client profiles. Extensive experimental analysis fully validates the superior quality and clinical fidelity of our dataset.Our datasets and evaluation framework are anonymously available at this repository.

Hyeongjun Yang, Donghyun Kim, Seokju Hwang, Midan Shim, KyuHwan Yeom, KaeHyun Um, Kyong-Ho Lee

Large language model (LLM)-based conversational recommender systems (CRSs) have demonstrated strong capabilities in capturing user preferences and generating contextually relevant recommendations. Nevertheless, the recommendation quality of the models frozen after training inevitably degrades under contextual shifts, such as changes in language and social trends. While periodic model updates are essential to maintain alignment with real-world preferences, training on large-scale data incurs substantial costs. This motivates data-efficient adaptation. However, existing data selection methods struggle to distinguish learnable samples under contextual shifts. To address this, we propose Contextual Shift-Adaptive Data Pruning and Training (CAPT), a framework agnostic to underlying LLM-based CRSs. Specifically, we conceptualize a three-class data taxonomy comprising familiar, valuable, and outlier samples to formalize data behavior under contextual shifts. Based on this taxonomy, we design an importance score estimation scheme that quantifies a sample’s relative learnability for shift adaptation. Leveraging these importance scores, CAPT prioritizes highly learnable samples and further guides shift-adaptive training to actively steer the model toward evolving preferences. Experiments on three CRS benchmarks with real-world temporal splits demonstrate that CAPT outperforms baselines, matching or surpassing full-data fine-tuning performance using only 10-50% of the training data.

Ragib Amin Nihal, Rui Wen, Kazuhiro Nakadai, Jun Sakuma

Large language models (LLMs) remain vulnerable to multi-turn jailbreaking attacks that exploit conversational context to bypass safety constraints gradually. These attacks target different harm categories through distinct conversational approaches. Existing multi-turn methods often rely on heuristic or ad hoc exploration strategies, providing limited insight into underlying model weaknesses. The relationship between conversation patterns and model vulnerabilities across harm categories remains poorly understood. We propose Pattern Enhanced Chain of Attack (PE-CoA), a framework of five conversation patterns to construct multi-turn jailbreaks through natural dialogue. Evaluating PE-CoA on twelve LLMs spanning ten harm categories, we achieve state-of-the-art performance, uncovering pattern-specific vulnerabilities and LLM behavioral characteristics: models exhibit distinct weakness profiles, defense to one pattern does not generalize to others, and model families share similar failure modes. These findings highlight limitations of safety training and indicate the need for pattern-aware defenses. Code available on: https://github.com/Ragib-Amin-Nihal/PE-CoA

Peng Zhou, Guangxin Li, Xiaoying Huang, Yiming Tang

Text simplification plays a vital role in natural language processing, yet auto long text simplification remains challenging due to the difficulty in the joint balancing of simplification efficiency and fine-grained quality requirements, such as fluency, grammatical correctness and semantic completeness. To address these challenges, we propose Simplify-Pro, a two-level and progressive LLM-based framework that establishes an effective paradigm for automatic long text simplification under diverse test scenarios. By integrating paragraph-level training, simplification generation, metric-assisted analysis and selective refinement into a unified multi-stage pipeline, our framework achieves superior performance across in-domain and out-of-domain simplification tasks, which matches or even outperforms advanced and proprietary LLMs. Furthermore, comprehensive experiments and qualitative analyses cover the simplification performance, generalization ability and the contribution of each individual stage, demonstrating the effectiveness, robustness and modular design advantages of Simplify-Pro.

Antonio De Santis, Tommaso Bonetti, Andrea Tocchetti, Marco Brambilla

The interpretation of implicit meanings is an integral aspect of human communication. However, this framework may not transfer to interactions with Large Language Models (LLMs). To investigate this, we introduce the task of Implicit Information Extraction (IIE) and propose an LLM-based IIE pipeline that builds a structured knowledge graph from a context sentence by extracting relational triplets, validating implicit inferences, and analyzing temporal relations. We evaluate two LLMs against crowdsourced human judgments on two datasets. We find that humans agree with most model triplets yet consistently propose many additions, indicating limited coverage in current LLM-based IIE. Moreover, in our experiments, models appear to be more conservative about implicit inferences than humans in socially rich contexts, whereas humans become more conservative in shorter, fact-oriented contexts. Our code is available at https://github.com/Antonio-Dee/IIE_from_LLM.

Shuang Cheng, Yihan Bian, Dawei Liu, Yuhua Jiang, Yihao Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo 等

Autoregressive (AR) language modeling remains the dominant paradigm due to its dense supervision signal and highly optimized serving infrastructure, but its strictly causal, token-by-token decoding limits parallelism and non-causal modeling. While masked diffusion offers a promising path toward parallel generation, it faces two critical bottlenecks: training inefficiency stemming from sparse masked objectives, and high latency caused by iterative whole-sequence denoising. We present a systematic study of blockwise discrete diffusion, a pragmatic middle ground that preserves AR-compatible serving while enabling parallel intra-block generation. Our study proceeds in four steps: (i) a controlled, compute- and scale-matched comparison revealing that AR is a more effective backbone for blockwise hybrids than masked diffusion objectives; (ii) a scalable conversion recipe, SDAR, validating that AR models spanning 1.7B to 30B parameters can be adapted into block diffusion models with minimal compute while preserving backbone capabilities; and (iii) a systematic characterization of decoding dynamics, which reveals a virtuous cycle where larger models enable more aggressive parallel decoding, achieving theoretical speedups over 5\times and wall-clock speedups of 2.3\times on H200 GPUs in latency-critical regimes; and (iv) an investigation of local non-causal modeling capabilities, showing that SDAR’s local bidirectional attention overcomes causal bottlenecks in scientific domains (e.g., chemistry) and enables robust test-time scaling. We release the full model suite, the training framework, and our inference engines for further innovation in non-autoregressive generative paradigms.

Allen Schmaltz

We introduce the Similarity-Distance-Magnitude (SDM) activation function, a more robust and interpretable formulation of the standard softmax activation function, adding Similarity (i.e., correctly predicted depth-matches into training) awareness and Distance-to-training-distribution awareness to the existing output Magnitude (i.e., decision-boundary) awareness, and enabling interpretability-by-exemplar via dense matching. We further introduce the SDM estimator, based on a data-driven partitioning of the class-wise empirical CDFs via the SDM activation, to control the class- and prediction-conditional accuracy among selective classifications. When used as the final-layer activation over pre-trained language models for selective classification, the SDM estimator is more robust to covariate shifts and out-of-distribution inputs than existing calibration methods using softmax activations, while remaining informative over in-distribution data.

Hanqi Jiang, Junhao Chen, Yi Pan, Ling Chen, Weihang You, Yifan Zhou, Ruidong Zhang, Yohannes Abate, Tianming Liu

While Large Language Models (LLMs) excel at generalized reasoning, standard retrieval-augmented approaches fail to address the disconnected nature of long-term agentic memory. To bridge this gap, we introduce Synapse (Synergistic Associative Processing Semantic Encoding), a unified memory architecture that transcends static vector similarity. Drawing from cognitive science, Synapse models memory as a dynamic graph where relevance emerges from spreading activation rather than pre-computed links. By integrating lateral inhibition and temporal decay, the system dynamically highlights relevant sub-graphs while filtering interference. We implement a Triple Hybrid Retrieval strategy that fuses geometric embeddings with activation-based graph traversal. Extensive evaluations on the LoCoMo benchmark show that Synapse significantly outperforms state-of-the-art methods in complex temporal and multi-hop reasoning tasks, offering a robust solution to the "Contextual Tunneling" problem.

Jaehoon Lee, CheolWon Na, Suyoung Bae, Jin-Seop Lee, Jihyung Lee, YunSeok Choi, Jee-Hyong Lee

Text-to-SQL enables users to query databases using natural language by generating executable SQL queries. Recent methods have increasingly adopted Large Language Models based reinforcement learning (RL) to leverage execution feedback for training. However, existing RL methods assign uniform query-level rewards to all clauses in a SQL query, treating correct and incorrect clauses equally. This coarse-grained reward design leads to insufficient learning signals for correct SQL generation. To address this issue, we propose **EXPO-SQL** (**EX**ecution-based clause-level **P**olicy **O**ptimization for Text-to-**SQL**) which provides fine-grained supervision through clause-level rewards. To assign clause-level rewards, our method identifies erroneous clauses by analyzing execution results, including error messages and clause-wise incremental execution. Experiments on widely-used Text-to-SQL benchmarks demonstrate that EXPO-SQL significantly outperforms existing supervised fine-tuning, prompting, and RL-based methods through fine-grained clause-level learning. Our code is available at https://github.com/jhn25/EXPO-SQL.

Ahmed Mahrous, Roberto Di Pietro

Emojis are widely used in online financial communication, but it is unclear whether they provide transferable sentiment signals across languages, platforms, and asset communities. This study examines the extent to which emoji usage, semantics, and sentiment polarity remain stable across financial communities, and how these layers influence zero-shot sentiment transfer. Using large corpora of Twitter and StockTwits posts in four languages, we measure cross-community divergence and evaluate sentiment models trained under emoji-only, text-only, and text+emoji inputs.We find that emoji frequencies differ across communities, especially across languages, but their semantics and sentiment polarity are largely stable. Cross-asset transferability shows minimal degradation, while cross-language transfer remains the most challenging. Including emojis consistently reduces transfer gaps relative to text-only models. These results indicate that financial communication exhibits a partially shared “emoji code,” and that emojis provide compact, language-independent sentiment cues that improve model generalization across markets and platforms.

Somraj Gautam, Anathapindika Dravichi, Gaurav Harit

We introduce INDOTABVQA, a benchmark for evaluating cross-lingual Table Visual Question Answering (VQA) on real-world document images in Bahasa Indonesia. The dataset comprises 1,593 document images across three visual styles (bordered, borderless, and colorful) with one or more tables, and 1,593 question-answer sets in four languages: Bahasa Indonesia, English, Hindi, and Arabic. This enables evaluation of Vision-Language Models (VLMs) in both monolingual (Bahasa documents with Bahasa questions) and cross-lingual settings (Bahasa documents with questions in other languages). We benchmark leading open-source VLMs (Qwen2.5-VL, Gemma- 3, LLaMA-3.2) and GPT-4o and reveal substantial performance gaps, particularly on structurally complex tables and in low-resource languages. Fine-tuning a compact 3B model and a LoRA- finetuned 7B model on our dataset yields 11.6% and 17.8% improvements in accuracy. Providing explicit table region coordinates as additional input further improves performance by 4-7%, demonstrating the value of Spatial priors for table-based reasoning. Our findings underscore the importance of language- diverse, domain-specific datasets and demonstrate that targeted fine-tuning can significantly enhance VLM performance on specialized document understanding tasks. INDOTABVQA provides a valuable resource for advancing research in cross-lingual, structure-aware document understanding, especially in underrepresented regions of the world. The dataset is publicly available via Hugging Face at: https://huggingface.co/datasets/NusaBharat/INDOTABVQA.

Minkyoung Kim, Daeun Ji, Yohan Lee, Beomsoo Kim, Beakcheol Jang

Time series forecasting underpins critical decision-making across diverse domains. While large language models (LLMs) offer promising reasoning capabilities, existing LLM-based time series forecasting approaches either reduce them to numerical predictors that bypass their strengths, or allow direct forecast generation that destabilizes predictions in non-stationary settings. We introduce CTRL, a framework that decouples semantic reasoning from quantitative prediction. A frozen backbone generates base forecasts, while specialized LLM agents function as controllers that analyze backbone prediction errors through decomposed trend, seasonal, and irregular components, grounding reasoning in interpretable temporal structure. Each agent outputs compact control signals that a lightweight residual decoder translates into forecast corrections. CTRL incorporates label-free test-time adaptation that detects distribution shift from input statistics alone and readapts control signals with only 3–24 LLM calls via caching. CTRL is explicitly designed to improve robustness under non-stationary temporal dynamics and distribution shift, while remaining competitive on highly stationary time series where adaptive correction provides limited additional benefit.

Beiduo Chen, Tiancheng Hu, Caiqi Zhang, Robert Litschko, Anna Korhonen, Barbara Plank

Reasoning-tuned LLMs utilizing long Chain-of-Thought (CoT) excel at single-answer tasks, yet their ability to model Human Label Variation—which requires capturing probabilistic ambiguity rather than resolving it—remains underexplored. We investigate this through systematic disentanglement experiments on distribution-based tasks, employing Cross-CoT experiments to isolate the effect of reasoning text from intrinsic model priors. We observe a distinct "decoupled mechanism": while CoT improves distributional alignment, final accuracy is dictated by CoT content (99% variance contribution), whereas distributional ranking is governed by model priors (over 80%). Step-wise analysis further shows that while CoT’s influence on accuracy grows monotonically during the reasoning process, distributional structure is largely determined by LLM’s intrinsic priors. These findings suggest that long CoT serves as a decisive LLM decision-maker for the top option but fails to function as a granular distribution calibrator for ambiguous tasks.

Seyun Bae, Seokhan Lee, Eunho Yang

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques overlook the need for continuous and immediate action, causing them to suffer from degraded utility as updates accumulate and protracted exposure of sensitive information. To address these issues, we propose **C**ontinual **U**nlearning in **R**e**a**l **T**ime with **E**nsured Preservation of LLM Knowledge (**CURaTE**). Our method begins by training a sentence embedding model on a dataset designed to enable the formation of sharp decision boundaries for determining whether a given input prompt corresponds to any stored forget requests. The similarity of a given input to the forget requests is then used to determine whether to answer or return a refusal response. We show that even with such a simple approach, not only does **CURaTE** achieve more effective forgetting than existing methods, but by avoiding modification of the language model parameters, it also maintains near perfect knowledge preservation over any number of updates and is the only method capable of continual unlearning in real-time.

Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang

Large Language Models (LLMs) encode substantial knowledge in their parameters, which can be located, traced, and analyzed. Despite recent progress in neural interpretability, it is still unclear how to transfer such knowledge in a fine-grained manner, namely parametric knowledge transfer (PKT). A central challenge is to make cross-scale transfer effective and efficient when source and target models differ in architecture and parameterization. Existing methods that directly reuse layer parameters are therefore strongly limited by neural incompatibility. In this paper, we identify latent semantic alignment as the key prerequisite for cross-scale knowledge transfer. Instead of directly moving layer parameters, our approach uses activations as the transfer medium. SemAlign has two stages: an layer attribution stage that attributes task-relevant source layers and selects exactly one source layer for each target layer, and a semantic alignment stage that pairs them from shallow to deep and optimizes the target with source-side supervisory hidden states. The alignment is carried out in latent space. In the current realization, training follows a shallow-to-deep frontier schedule: at each stage, only the current target layer is trainable, the layer objective is a Fisher-weighted quadratic surrogate on target-space aligned logits, and the final output layer keeps KL distillation. The transferred object nonetheless remains the aligned representation itself. Evaluations on four benchmarks demonstrate the efficacy of our method. Further analysis reveals the key factors that ease cross-scale knowledge transfer and provides insights into the nature of latent semantic alignment.

Gustavo Cilleruelo Calderón, Mahrad Almotahari, Emily Allaway, Barry Haddow, Alexandra Birch

Generic sentences express generalizations that tolerate exceptions without explicitly communicating information about quantities. For example, the sentence Ravens are black is true even though there are albino ravens. The sentence doesn’t explicitly communicate the number or frequency of black ravens. Whether generics semantically encode information about quantities implicitly is controversial. This work takes a large-scale distributional approach to the semantic debate. It compares thousands of naturally occurring generics and quantificational sentences using language-model probabilities. It shows that language models recover many semantic facts about quantifiers. It also shows that they recover semantic facts about surface distributional differences between generics and their “quantificational counterparts”. Accordingly, and contrary to dominant views in other fields, we formulate an empirical argument to the effect that generics are not quantificational.

Yamen Ajjour, Carlotta Quensel, Nedim Lipka, Henning Wachsmuth

Argumentation skills are an essential toolkit for large language models (LLMs). These skills are crucial in various use cases, including self-reflection, debating collaboratively for diverse answers, and countering hate speech. In this paper, we create the first benchmark for a standardized evaluation of LLM-based approaches to computational argumentation, encompassing 33 datasets from previous work in unified form. Using the benchmark, we evaluate the generalizability of five LLM families across 46 computational argumentation tasks that cover mining arguments, assessing perspectives, assessing argument quality, reasoning about arguments, and generating arguments. On the benchmark, we conduct an extensive systematic analysis of the contribution of few-shot examples, reasoning steps, model size, and training skills to the performance of LLMs on the computational argumentation tasks in the benchmark.

Omri Asscher, Arif Ahmad, Ananya Agrawal, Monojit Choudhury

Translation is a fundamentally value-laden process that requires the translator to make decisions and judgments that have ethical implications. However, even though large language models (LLMs) are increasingly used for translation tasks, LLMs have not been systematically examined for their default ethical tendencies or their abilities to employ and prioritize specified ethical approaches in conflicted translation situations. To address this gap, we present ETHICA-MT, a framework for examining ethical reasoning and implementation in LLM-based machine translation. Drawing on diverse ethical approaches from the translation studies literature, we formalize a conceptual framework and construct a multilingual benchmark, ETHICA-MT BENCH, that covers six languages and highlights ethical conflicts arising from competing ethical approaches in a variety of translation scenarios. Our empirical study shows that current models predominantly default to an ethical stance favoring ‘faithful representation’ to the source text, and vary in their ability to implement specified ethics at the expense of others. Finally, we highlight the basic challenges of automatically and manually evaluating the models’ ethical stances.