Natural Language Processing Techniques

Derniers papiers

• SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification

  Tianyang Zhou, Ziyi Zhang, Haowen Lin, Somesh Jha, Mihai Christodorescu, Kirill Levchenko, Varun Chandrasekaran · 24 décembre 2025

  Translating software written in C to Rust has significant benefits in improving memory safety. However, manual translation is cumbersome, error-prone, and often produces unidiomatic code. Large language models (LLMs) have demonstrated promise in producing idiomatic translations, but offer no correct…

• Automatic Detection of LLM-Generated Code: A Comparative Case Study of Contemporary Models Across Function and Class Granularities

  Musfiqur Rahman, SayedHassan Khatoonabadi, Ahmad Abdellatif, Emad Shihab · 23 décembre 2025

  The adoption of Large Language Models (LLMs) for code generation risks incorporating vulnerable code into software systems. Existing detectors face two critical limitations: a lack of systematic cross-model validation and opaque "black box" operation. We address this through a comparative study of c…

• MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning

  Tao Zhang, Ziqian Zeng, Hao Peng, Huiping Zhuang, Cen Chen · 23 décembre 2025

  Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although KV cache quantization is a promising compression technique,…

• GraphShaper: Geometry-aware Alignment for Improving Transfer Learning in Text-Attributed Graphs

  Heng Zhang, Tianyi Zhang, Yuling Shi, Xiaodong Gu, Yaomin Shen, Haochen You, Zijian Zhang, Yilei Yuan, Jin Huang · 23 décembre 2025

  Graph foundation models represent a transformative paradigm for learning transferable representations across diverse graph domains. Recent methods leverage large language models to unify graph and text modalities into a shared representation space using contrastive learning. However, systematic eval…

• Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric

  Yan Shvartzshnaider, Vasisht Duddu · 22 décembre 2025

  As large language models (LLMs) are integrated into sociotechnical systems, it is crucial to examine the privacy biases they exhibit. We define privacy bias as the appropriateness value of information flows in responses from LLMs. A deviation between privacy biases and expected values, referred to a…

• MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair

  Ali Reza Ibrahimzada, Brandon Paulsen, Reyhaneh Jabbarvand, Joey Dodds, Daniel Kroening · 22 décembre 2025

  Code translation transforms source code from one programming language (PL) to another. Validating the functional equivalence of translation and repairing, if necessary, are critical steps in code translation. Existing automated validation and repair approaches struggle to generalize to many PLs due …

• On the Effect of Sampling Diversity in Scaling LLM Inference

  Tianchun Wang, Zichuan Liu, Yuanzhou Chen, Jonathan Light, Weiyang Liu, Haifeng Chen, Xiang Zhang, Wei Cheng · 22 décembre 2025

  Large language model (LLM) scaling inference is key to unlocking greater performance, and leveraging diversity has proven an effective way to enhance it. Motivated by the observed relationship between solution accuracy and meaningful response diversity, we systematically study the effect of prompt d…

• DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

  Hao Liang, Xiaochen Ma, Zhou Liu, Zhen Hao Wong, Zhengyang Zhao, Zimo Meng, Runming He, Chengyu Shen, Qifeng Cai, Zhaoyang Han, Meiyi Qiang, Yalin Feng, Tianyi Bai, Zewei Pan, Ziyi Guo, Yizhen Jiang, Jingwen Deng, Qijie You, Peichao Lai, Tianyu Guo, Chi Hsu Tsai, Hengyi Feng, Rui Hu, Wenkai Yu, Junbo Niu, Bohan Zeng, Ruichuan An, Lu Ma, Jihao Huang, Yaowei Zheng, Conghui He, Linpeng Tang, Bin Cui, Weinan E, Wentao Zhang · 19 décembre 2025

  The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc scripts and loosely specified workflows, which lack principled abs…

• Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers

  Thanh Dat Hoang, Thanh Tam Nguyen, Thanh Trung Huynh, Hongzhi Yin, Quoc Viet Hung Nguyen · 19 décembre 2025

  Most modern Text2SQL systems prompt large language models (LLMs) with entire schemas -- mostly column information -- alongside the user's question. While effective on small databases, this approach fails on real-world schemas that exceed LLM context limits, even for commercial models. The recent Spi…

• An Information-Theoretic Framework for Robust Large Language Model Editing

  Qizhou Chen, Chengyu Wang, Taolin Zhang, Xiaofeng He · 19 décembre 2025

  Large Language Models (LLMs) have become indispensable tools in science, technology, and society, enabling transformative advances across diverse fields. However, errors or outdated information within these models can undermine their accuracy and restrict their safe deployment. Developing efficient …

• TOGGLE: Temporal Logic-Guided Large Language Model Compression for Edge

  Khurram Khalil, Khaza Anuarul Hoque · 19 décembre 2025

  Large Language Models (LLMs) deliver exceptional performance across natural language tasks but demand substantial computational resources, limiting their deployment on resource-constrained edge devices. Existing compression techniques, such as quantization and pruning, often degrade critical linguis…

• Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs

  William English, Dominic Simon, Sumit Kumar Jha, Rickard Ewetz · 19 décembre 2025

  Translating natural language (NL) into a formal language such as temporal logic (TL) is integral for human communication with robots and autonomous systems. State-of-the-art approaches decompose the task into a lifting of atomic propositions (APs) phase and a translation phase. However, existing met…

• Yes-MT's Submission to the Low-Resource Indic Language Translation Shared Task in WMT 2024

  Yash Bhaskar, Parameswari Krishnamurthy · 18 décembre 2025

  This paper presents the systems submitted by the Yes-MT team for the Low-Resource Indic Language Translation Shared Task at WMT 2024 (Pakray et al., 2024), focusing on translating between English and the Assamese, Mizo, Khasi, and Manipuri languages. The experiments explored various approaches, incl…

• LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients

  Egor Fadeev, Dzhambulat Mollaev, Aleksei Shestov, Omar Zoloev, Artem Sakhno, Dmitry Korolev, Ivan Kireev, Andrey Savchenko, Maksim Makarenko · 18 décembre 2025

  Learning clients embeddings from sequences of their historic communications is central to financial applications. While large language models (LLMs) offer general world knowledge, their direct use on long event sequences is computationally expensive and impractical in real-world pipelines. In this p…

• DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration

  Tianteng Gu, Bei Liu, Bo Xiao, Ke Zeng, Jiacheng Liu, Yanmin Qian · 18 décembre 2025

  Pruning is a widely used technique to compress large language models (LLMs) by removing unimportant weights, but it often suffers from significant performance degradation - especially under semi-structured sparsity constraints. Existing pruning methods primarily focus on estimating the importance of…

• FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference

  Guangda Liu, Chengwei Li, Zhenyu Ning, Jing Lin, Yiwu Yao, Danning Ke, Minyi Guo, Jieru Zhao · 17 décembre 2025

  Large language models (LLMs) have been widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size grows proportionally with context length. While KV cac…

• RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation

  Yanli Wang, Yanlin Wang, Suiquan Wang, Daya Guo, Jiachi Chen, John Grundy, Xilin Liu, Yuchi Ma, Mingzhi Mao, Hongyu Zhang, Zibin Zheng · 17 décembre 2025

  Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the performance of such code translators. However, previous benchmark…

• A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs

  K. M. Jubair Sami, Dipto Sumit, Ariyan Hossain, Farig Sadeque · 17 décembre 2025

  Translating from a standard language to its regional dialects is a significant NLP challenge due to scarce data and linguistic variation, a problem prominent in the Bengali language. This paper proposes and compares two novel RAG pipelines for standard-to-dialectal Bengali translation. The first, a …

• Towards Nepali-language LLMs: Efficient GPT training with a Nepali BPE tokenizer

  Adarsha Shrestha, Basanta Pokharel, Binit Shrestha, Smriti Adhikari, Dinesh Gothe · 17 décembre 2025

  Nepali, a low-resource language spoken by over 32 million people, continues to face challenges in natural language processing (NLP) due to its complex grammar, agglutinative morphology, and limited availability of high-quality corpora. Most efforts to date have centered on basic encoder architecture…

• Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving

  Fangzhou Wu, Sandeep Silwal · 16 décembre 2025

  Increasing demand for Large Language Models (LLMs) services imposes substantial deployment and computation costs on providers. LLM routing offers a cost-efficient solution by directing queries to the optimal LLM based on model and query features. However, existing works primarily focus on offline sc…

• Synthetic bootstrapped pretraining

  Zitong Yang, Aonan Zhang, Hong Liu, Tatsunori Hashimoto, Emmanuel Cand\`es, Chong Wang, Ruoming Pang · 16 décembre 2025

  We introduce Synthetic Bootstrapped Pretraining (SBP), a language model (LM) pretraining procedure that first learns a model of relations between documents from the pretraining dataset and then leverages it to synthesize a vast new corpus for joint training. While the standard pretraining teaches LM…

• VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs

  Avinash Amballa, Yashas Malur Saidutta, Chi-Heng Lin, Vivek Kulkarni, Srinivas Chappidi · 16 décembre 2025

  Large language models (LLMs) are increasingly being used to generate synthetic datasets for the evaluation and training of downstream models. However, prior work has noted that such generated data lacks diversity. In this paper, we propose Voyager, a novel principled approach to generate diverse dat…

• Temporal Tokenization Strategies for Event Sequence Modeling with Large Language Models

  Zefang Liu, Nam Nguyen, Yinzhu Quan, Austin Zhang · 16 décembre 2025

  Representing continuous time is a critical and under-explored challenge in modeling temporal event sequences with large language models (LLMs). Various strategies like byte-level representations or calendar tokens have been proposed. However, the optimal approach remains unclear, especially given th…

• Improving Generative Ad Text on Facebook using Reinforcement Learning

  Daniel R. Jiang, Alex Nikulkov, Yu-Chia Chen, Yang Bai, Zheqing Zhu · 16 décembre 2025

  Generative artificial intelligence (AI), in particular large language models (LLMs), is poised to drive transformative economic change. LLMs are pre-trained on vast text data to learn general language patterns, but a subsequent post-training phase is critical to align them for specific real-world ta…

• SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs

  Parsa Hosseini, Sumit Nawathe, Mazda Moayeri, Sriram Balasubramanian, Soheil Feizi · 16 décembre 2025

  Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision. In this paper, we investigate spurious bias in MLLMs and introduce SpurLens, a pipeline that leverage…