论文检索

Emma Harvey, Emily Sheng, Su Lin Blodgett, Alexandra Chouldechova, Jean Garcia-Gathright, Alexandra Olteanu, Hanna Wallach

The NLP research community has made publicly available numerous instruments for measuring representational harms caused by large language model (LLM)-based systems. These instruments have taken the form of datasets, metrics, tools, and more. In this paper, we examine the extent to which such instruments meet the needs of practitioners tasked with evaluating LLM-based systems. Via semi-structured interviews with 12 such practitioners, we find that practitioners are often unable to use publicly available instruments for measuring representational harms. We identify two types of challenges. In some cases, instruments are not useful because they do not meaningfully measure what practitioners seek to measure or are otherwise misaligned with practitioner needs. In other cases, instruments-even useful instruments-are not used by practitioners due to practical and institutional barriers impeding their uptake. Drawing on measurement theory and pragmatic measurement, we provide recommendations for addressing these challenges to better meet practitioner needs.

Ding Yu, Zhuo Liu, Hangfeng He

Post-earnings volatility prediction is critical for investors, with previous works often leveraging earnings call transcripts under the assumption that their rich semantics contribute significantly. To further investigate how transcripts impact volatility, we introduce DEC, a dataset featuring accurate volatility calculations enabled by the previously overlooked beforeAfterMarket attribute and dense ticker coverage. Unlike established benchmarks, where each ticker has only around two earnings, DEC provides 20 earnings records per ticker. Using DEC, we reveal that post-earnings volatility undergoes significant shifts, with each ticker displaying a distinct volatility distribution. To leverage historical post-earnings volatility and capture ticker-specific patterns, we propose two training-free baselines: Post-earnings Volatility (PEV) and Same-ticker Post-earnings Volatility (STPEV). These baselines surpass all transcripts-based models on DEC as well as on established benchmarks. Additionally, we demonstrate that current transcript representations predominantly capture ticker identity rather than offering financially meaningful insights specific to each earnings. This is evidenced by two key observations: earnings representations from the same ticker exhibit significantly higher similarity compared to those from different tickers, and predictions from transcript-based models show strong correlations with prior post-earnings volatility.

Zhaoyang Xia, Somdeb Sarkhel, Mehrab Tanjim, Stefano Petrangeli, Ishita Dasgupta, Yuxiao Chen, Jinxuan Xu, Di Liu, Saayan Mitra, Dimitris N. Metaxas

Ideation, the process of forming ideas from concepts, is a big part of the content creation process. However, the noble goal of helping visual content creators by suggesting meaningful sequences of visual assets from a limited collection is challenging. It requires a nuanced understanding of visual assets and the integration of open-world knowledge to support creative exploration. Despite its importance, this task has yet to be explored fully in existing literature. To fill this gap, we propose Visual Story Ideation, a novel and underexplored task focused on the automated selection and arrangement of visual assets into coherent sequences that convey expressive storylines.We also present VISIAR, Visual Ideation through Sequence Integration and Asset Rearrangement, a robust framework leveraging Multimodal Large Language Models (MLLMs), and a novel Story Graph mechanism. Our framework operates in three key stages: visual content understanding, candidate asset selection, and asset rearrangement via MLLMs. In addition, we curated a new benchmark dataset, called VTravel, to evaluate our methods both qualitatively and quantitatively.User studies and GPT-as-the-judge evaluation show that our approach surpasses GPT-4o based baseline by an average of 33.5% and 18.5% across three different metrics, demonstrating the effectiveness of our framework for generating compelling visual stories.

Tong Zheng, Yan Wen, Huiwen Bao, Junfeng Guo, Heng Huang

The emergence of Large Language Models (LLMs) has advanced the multilingual machine translation (MMT), yet the Curse of Multilinguality (CoM) remains a major challenge. Existing work in LLM-based MMT typically mitigates this issue via scaling up training and computation budget, which raises a critical question: Is scaling up the training and computation budget truly necessary for high-quality MMT, or can a deeper understanding of CoM provide a more efficient solution? To explore this problem, we analyze the linguistic conflicts and synergy, the underlying mechanism of CoM during post-training phase. We identify an asymmetric phenomenon in linguistic conflicts and synergy: the dominance of conflicts and synergy varies in different translation directions, leading to sub-optimal adaptation in existing post-training methods. We further find that a significant bottleneck in MMT appears to lie in post-training rather than multilingual pre-training, suggesting the need for more effective adaptation strategies. Building on these new insights, we propose a direction-aware training approach, combined with group-wise model merging, to address asymmetry in linguistic conflicts and synergy explicitly. Leveraging this strategy, our method fine-tunes X-ALMA-13B-Pretrain—trained only with multilingual pre-training—achieving comparable performance to XALMA-13B (only SFT) while using only 20B pretraining tokens and 17B parameters—5.5× fewer pretraining-tokens and 1.7x fewer model size—with just 0.85 COMET drop on Flores-200 testsets of 50 languages.

Ke Yi, Jianwei Zhang, Zhiying Xu, Xinlong Yang, Yang Zhou, Minmin Sun, Zengke Liu, Tong Zhang, Junyang Lin, Jingren Zhou

Auto-regressive decoding is a memory-bound job, meaning decoding inference performance is limited by the bandwidth rather than the computational capabilities of the GPU. Weight-only quantization is a promising method to address the memory-bound limitations. Previous studies have followed one of two approaches. Some have exclusively studied integer quantization while ignoring the Gaussian distribution nature of LLMs’ weights. Others have proposed non-uniform quantization but incurred additional I/O overhead due to lookup tables, e.g. NF4. In this work, we extend the IEEE 754 float-point standard to the ExMy quantization schema, which allocates x bit for the exponent and y bit for the mantissa to represent a number. In terms of runtime efficiency, we demonstrate that the conversion from ExMy to FP16 can be realized through register-level operations, which can get almost the same performance as INT5. In terms of quantization loss, we analyze that of different ExMy settings, where the E2M2 schema achieves an optimal balance, offering the highest efficiency with lossless accuracy. We further propose the FPE2M2 framework that supports lossless weight-only quantization inference and validate the FPE2M2 framework on Qwen and LLaMA Models across various modalities, such as text, image, and audio tasks, which achieves a faster inference speed while maintaining nearly lossless accuracy.

Denitsa Saynova, Lovisa Hagström, Moa Johansson, Richard Johansson, Marco Kuhlmann

Language models (LMs) can make a correct prediction based on many possible signals in a prompt, not all corresponding to recall of factual associations. However, current interpretations of LMs fail to take this into account. For example, given the query “Astrid Lindgren was born in” with the corresponding completion “Sweden”, no difference is made between whether the prediction was based on knowing where the author was born or assuming that a person with a Swedish-sounding name was born in Sweden. In this paper, we present a model-specific recipe - PrISM - for constructing datasets with examples of four different prediction scenarios: generic language modeling, guesswork, heuristics recall and exact fact recall. We apply two popular interpretability methods to the scenarios: causal tracing (CT) and information flow analysis. We find that both yield distinct results for each scenario. Results for exact fact recall and generic language modeling scenarios confirm previous conclusions about the importance of mid-range MLP sublayers for fact recall, while results for guesswork and heuristics indicate a critical role of late last token position MLP sublayers. In summary, we contribute resources for a more extensive and granular study of fact completion in LMs, together with analyses that provide a more nuanced understanding of how LMs process fact-related queries.

Yongjia Lei, Haoyu Han, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M Halappanavar, Jiliang Tang, Yu Wang

Text-rich Graph Knowledge Bases (TG-KBs) have become increasingly crucial for answering queries by providing textual and structural knowledge. However, current retrieval methods often retrieve these two types of knowledge in isolation without considering their mutual reinforcement and existing hybrid methods even bypass structural retrieval entirely. To fill this gap, we propose a Mixture of Structural-and-Textual Retrieval (MoR) to retrieve these two types of knowledge via a Planning-Reasoning-Organizing framework. In the Planning stage, MoR generates textual planning graphs delineating the logic for answering queries. Following planning graphs, in the Reasoning stage, MoR interweaves structural traversal and textual matching to obtain candidates from TG-KBs. In the Organizing stage, MoR further reranks fetched candidates based on their structural trajectory. Extensive experiments demonstrate the superiority of MoR in harmonizing structural and textual retrieval with inspiring insights, including imbalanced retrieving performance across different query logics and the benefits of integrating structural trajectories for candidate reranking.

Steven Koniaev, Ori Ernst, Jackie CK Cheung

Despite recent advancements in automatic summarization, state-of-the-art models do not summarize all documents equally well, raising the question: why? While prior research has extensively analyzed summarization models, little attention has been given to the role of document characteristics in influencing summarization performance.In this work, we explore two key research questions. First, do documents exhibit consistent summarization quality across multiple systems? If so, can we predict a document’s summarization performance without generating a summary? We answer both questions affirmatively and introduce PreSumm, a novel task in which a system predicts summarization performance based solely on the source document. Our analysis sheds light on common properties of documents with low PreSumm scores, revealing that they often suffer from coherence issues, complex content, or a lack of a clear main theme.In addition, we demonstrate PreSumm’s practical utility in two key applications: improving hybrid summarization workflows by identifying documents that require manual summarization and enhancing dataset quality by filtering outliers and noisy documents.Overall, our findings highlight the critical role of document properties in summarization performance and offer insights into the limitations of current systems that could serve as the basis for future improvements.

Philipp Christmann, Gerhard Weikum

Question answering over mixed sources, like text and tables, has been advanced by verbalizing all contents and encoding it with a language model. A prominent case of such heterogeneous data is personal information: user devices log vast amounts of data every day, such as calendar entries, workout statistics, shopping records, streaming history, and more. Information needs range from simple look-ups to queries of analytical nature. The challenge is to provide humans with convenient access with small footprint, so that all personal data stays on the user devices. We present ReQAP, a novel method that creates an executable operator tree for a given question, via recursive decomposition. Operators are designed to enable seamless integration of structured and unstructured sources, and the execution of the operator tree yields a traceable answer. We further release the PerQA benchmark, with persona-based data and questions, covering a diverse spectrum of realistic user needs.

Chaoran Chen, Bingsheng Yao, Ruishi Zou, Wenyue Hua, Weimin Lyu, Toby Jia-Jun Li, Dakuo Wang

Role-Playing Agent (RPA) is an increasingly popular type of LLM Agent that simulates human-like behaviors in a variety of tasks. However, evaluating RPAs is challenging due to diverse task requirements and agent designs.This paper proposes an evidence-based, actionable, and generalizable evaluation design guideline for LLM-based RPA by systematically reviewing 1,676 papers published between Jan. 2021 and Dec. 2024.Our analysis identifies six agent attributes, seven task attributes, and seven evaluation metrics from existing literature.Based on these findings, we present an RPA evaluation design guideline to help researchers develop more systematic and consistent evaluation methods.

Jorge Iranzo-Sánchez, Javier Iranzo-Sánchez, Adrià Giménez, Jorge Civera

Current evaluation practices in Simultaneous Speech Translation (SimulST) systems typically involve segmenting the input audio and corresponding translations, calculating quality and latency metrics for each segment, and averaging the results. Although this approach may provide a reliable estimation of translation quality, it can lead to misleading values of latency metrics due to an inherent assumption that average latency values are good enough estimators of SimulST systems’ response time. However, our detailed analysis of latency evaluations for state-of-the-art SimulST systems demonstrates that latency distributions are often skewed and subject to extreme variations. As a result, the mean in latency metrics fails to capture these anomalies, potentially masking the lack of robustness in some systems and metrics. In this paper, a thorough analysis of the results of systems submitted to recent editions of the IWSLT simultaneous track is provided to support our hypothesis and alternative ways to report latency metrics are proposed in order to provide a better understanding of SimulST systems’ latency.

Szymon Kobus, Deniz Gunduz

Speculative decoding accelerates large language model inference using a smaller draft model. In this paper, we establish a surprising connection between speculative sampling and the concept of channel simulation from information theory, which aims at simulating a noisy channel using as few bits as possible. This connection allows us to provide an information-theoretic analysis of the speed up that can be achieved by speculative sampling. Leveraging this link, we derive an explicit relation between generation speed-up and the number of tokens k generated by the draft model for large k, which serves as an upper bound for all k. We also propose a novel speculative sampling method via exponential races called ERSS that matches state-of-the-art performance.

Xueliang Zhao, Wei Wu, Jian Guan, Lingpeng Kong

The ability of large language models to solve complex mathematical problems has progressed significantly, particularly for tasks requiring advanced reasoning. However, the scarcity of sufficiently challenging problems, particularly at the Olympiad level, hinders further advancements. In this work, we introduce PromptCoT, a novel approach for automatically generating high-quality Olympiad-level math problems. The proposed method synthesizes complex problems based on mathematical concepts and the rationale behind problem construction, emulating the thought processes of experienced problem designers. We provide a theoretical analysis demonstrating that an optimal rationale should maximize both the likelihood of rationale generation given the associated concepts and the likelihood of problem generation conditioned on both the rationale and the concepts. Our method is evaluated on standard benchmarks including GSM8K, MATH-500, and AIME2024, where it consistently outperforms existing problem generation methods. Furthermore, we demonstrate that PromptCoT exhibits superior scalability, consistently maintaining high performance as the dataset size increases, outperforming the baselines.

Alexey Tikhonov, Sergei Shteiner, Anna Bykova, Ivan P. Yamshchikov

Russenorsk, a pidgin language historically used in trade interactions between Russian and Norwegian speakers, represents a unique linguistic phenomenon. In this paper, we attempt to analyze its lexicon using modern large language models (LLMs), based on surviving literary sources. We construct a structured dictionary of the language, grouped by synonyms and word origins. Subsequently, we use this dictionary to formulate hypotheses about the core principles of word formation and grammatical structure in Russenorsk and show which hypotheses generated by large language models correspond to the hypotheses previously proposed ones in the academic literature. We also develop a “reconstruction” translation agent that generates hypothetical Russenorsk renderings of contemporary Russian and Norwegian texts.

Shuliang Liu, Hongyi Liu, Aiwei Liu, Duan Bingchen, Zheng Qi, Yibo Yan, He Geng, Peijie Jiang, Jia Liu, Xuming Hu

The widespread deployment of large language models (LLMs) across critical domains has amplified the societal risks posed by algorithmically generated misinformation. Unlike traditional false content, LLM-generated misinformation can be self-reinforcing, highly plausible, and capable of rapid propagation across multiple languages, which traditional detection methods fail to mitigate effectively. This paper introduces a proactive defense paradigm, shifting from passive post hoc detection to anticipatory mitigation strategies. We propose a Three Pillars framework: (1) Knowledge Credibility, fortifying the integrity of training and deployed data; (2) Inference Reliability, embedding self-corrective mechanisms during reasoning; and (3) Input Robustness, enhancing the resilience of model interfaces against adversarial attacks. Through a comprehensive survey of existing techniques and a comparative meta-analysis, we demonstrate that proactive defense strategies offer up to 63% improvement over conventional methods in misinformation prevention, despite non-trivial computational overhead and generalization challenges. We argue that future research should focus on co-designing robust knowledge foundations, reasoning certification, and attack-resistant interfaces to ensure LLMs can effectively counter misinformation across varied domains.

Zitao Xuan, Xiaofeng Mao, Da Chen, Xin Zhang, Yuhan Dong, Jun Zhou

In light of the widespread deployment of Large Language Models (LLMs), the responsibility for safeguarding and regulating LLM-generated content has taken on heightened significance. Recent advancements in LLM-based moderation methods, e.g., LlamaGuard, have demonstrated remarkable promise in identifying safety risks associated with both inputs and outputs in human-AI interactions. However, integrating LLM-based safeguards into a chatbot system requires an additional inference stage involving a moderation LLM with billions of parameters, which significantly increases computational costs and reduces overall efficiency. In this paper, we demonstrate that simply learning a classification head on the last-layer hidden states of the dialogue model provides a strong capability to identify harmful contents. The classification head, referred to as ShieldHead, serves as an auxiliary branch paralleled with next-token-prediction LM head, enabling the detection of potential risks in past text sequences. Additionally, a label disambiguation technique is employed to supervise ShieldHead with both token-level and sentence-level labels, which further enhances its performance. ShieldHead exhibits remarkable efficiency during inference, providing real-time moderation results alongside token-wise streaming output during the chatbot system’s decoding phase. Extensive experimental results demonstrate the superiority of the proposed framework: a state-of-the-art performance on the XSTest and SafeRLHF datasets while running at a speed about **300×** faster (**<1ms**) than previous LLM-based moderation models with ** 99%** less parameters of LlamaGuard.

Benedikt Ebing, Goran Glavaš

Translation-based strategies for cross-lingual transfer XLT such as translate-train—training on noisy target language data translated from the source language—and translate-test—evaluating on noisy source language data translated from the target language—are competitive XLT baselines. In XLT for token classification tasks, however, these strategies include label projection, the challenging step of mapping the labels from each token in the original sentence to its counterpart(s) in the translation. Although word aligners (WAs) are commonly used for label projection, the low-level design decisions for applying them to translation-based XLT have not been systematically investigated. Moreover, recent marker-based methods, which project labeled spans by inserting tags around them before (or after) translation, claim to outperform WAs in label projection for XLT. In this work, we revisit WAs for label projection, systematically investigating the effects of low-level design decisions on token-level XLT: (i) the algorithm for projecting labels between (multi-)token spans, (ii) filtering strategies to reduce the number of noisily mapped labels, and (iii) the pre-tokenization of the translated sentences. We find that all of these substantially impact translation-based XLT performance and show that, with optimized choices, XLT with WA offers performance at least comparable to that of marker-based methods. We then introduce a new projection strategy that ensembles translate-train and translate-test predictions and demonstrate that it substantially outperforms the marker-based projection. Crucially, we show that our proposed ensembling also reduces sensitivity to low-level WA design choices, resulting in more robust XLT for token classification tasks.

Shimao Zhang, Xiao Liu, Xin Zhang, Junxiao Liu, Zheheng Luo, Shujian Huang, Yeyun Gong

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs’ performance, which is constrained by the upper limit of human performance. Therefore, Self-Rewarding method has been proposed, where LLMs generate training data by rewarding their own outputs. However, the existing self-rewarding paradigm is not effective in mathematical reasoning scenarios and may even lead to a decline in performance. In this work, we propose the Process-based Self-Rewarding pipeline for language models, which introduces long-thought reasoning, step-wise LLM-as-a-Judge, and step-wise preference optimization within the self-rewarding paradigm. Our new paradigm successfully enhances the performance of LLMs on multiple mathematical reasoning benchmarks through iterative Process-based Self-Rewarding, demonstrating the immense potential of process-based self-rewarding to achieve LLM reasoning that may surpass human capabilities.

Kushan Mitra, Dan Zhang, Sajjadur Rahman, Estevam Hruschka

Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation. To verify LLM-generated contents and claims from other sources, traditional verification approaches often rely on holistic models that assign a single factuality label to complex claims, potentially obscuring nuanced errors. In this paper, we advocate for a shift towards fine-grained verification, where complex claims are broken down into smaller sub-claims for individual verification, allowing for more precise identification of inaccuracies, improved transparency, and reduced ambiguity in evidence retrieval. However, generating sub-claims poses challenges, such as maintaining context and ensuring semantic equivalence with respect to the original claim. We introduce **FactLens**, a benchmark for evaluating fine-grained fact verification, with metrics and automated evaluators of sub-claim quality. The benchmark data is manually curated to ensure high-quality ground truth. Our results show alignment between automated FactLens evaluators and human judgments, and we discuss the impact of sub-claim characteristics on the overall verification performance.

Wujiang Xu, Yunxiao Shi, Zujie Liang, Xuying Ning, Kai Mei, Kun Wang, Xi Zhu, Min Xu, Yongfeng Zhang

Traditional recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform’s recommendation algorithms. However, the defect of recommendation algorithms may put users in very vulnerable positions under this paradigm. First, many sophisticated models are often designed with commercial objectives in mind, focusing on the platform’s benefits, which may hinder their ability to protect and capture users’ true interests. Second, these models are typically optimized using data from all users, which may overlook individual user’s preferences. Due to these shortcomings, users may experience several disadvantages under the traditional user-platform direct exposure paradigm, such as lack of control over the recommender system, potential manipulation by the platform, echo chamber effects, or lack of personalization for less active users due to the dominance of active users during collaborative learning. Therefore, there is an urgent need to develop a new paradigm to protect user interests and alleviate these issues. Recently, some researchers have introduced LLM agents to simulate user behaviors, these approaches primarily aim to optimize platform-side performance, leaving core issues in recommender systems unresolved. To address these limitations, we propose a new user-agent-platform paradigm, where agent serves as the protective shield between user and recommender system that enables indirect exposure. To this end, we first construct four recommendation datasets, denoted as InstructRec, along with user instructions for each record. To understand user’s intention, we design an Instruction-aware Agent capable of using tools to acquire knowledge from external environments. Moreover, we introduce an Individual Instruction-aware Agent, which incorporates a dynamic memory mechanism to optimize from individual feedback. Results on four datasets demonstrate that consistently achieves an average improvement of 16.6% over SOTA baselines across ranking metrics. Moreover, iAgent mitigates echo chamber effects and effectively alleviates the model bias in disadvantaged users (less-active), serving as a shield between user and recommender systems.