Natural Language Processing Techniques

Neueste Paper

• IndicDB -- Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages

  Aviral Dawar, Roshan Karanth, Vikram Goyal, Dhruv Kumar · 16. April 2026

  While Large Language Models (LLMs) have significantly advanced Text-to-SQL performance, existing benchmarks predominantly focus on Western contexts and simplified schemas, leaving a gap in real-world, non-Western applications. We present IndicDB, a multilingual Text-to-SQL benchmark for evaluating c…

• Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models

  Mehrzad Samadi, Aleksander Ficek, Sean Narenthiran, Siddhartha Jain, Wasi Uddin Ahmad, Somshubra Majumdar, Vahid Noroozi, Boris Ginsburg · 16. April 2026

  Competitive programming has become a rigorous benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). The International Olympiad in Informatics (IOI) stands out as one of the most prestigious annual competitions in competitive programming and has beco…

• English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training

  Mehak Dhaliwal, Shashwat Chaurasia, Yao Qin, Dezhi Hong, Thomas Butler · 16. April 2026

  Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to performance disparities across languages. We present a systematic, controlled study of the interplay between training language coverage, model scale,…

• Lossless Prompt Compression via Dictionary-Encoding and In-Context Learning: Enabling Cost-Effective LLM Analysis of Repetitive Data

  Andresa Rodrigues de Campos, David Lee, Imry Kissos, Piyush Paritosh · 16. April 2026

  In-context learning has established itself as an important learning paradigm for Large Language Models (LLMs). In this paper, we demonstrate that LLMs can learn encoding keys in-context and perform analysis directly on encoded representations. This finding enables lossless prompt compression via dic…

• Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles

  Matthew C. Kelley · 15. April 2026

  Forced alignment is a common tool to align audio with orthographic and phonetic transcriptions. Most forced alignment tools provide only point-estimates of boundaries. The present project introduces a method of producing gradient boundaries by deriving confidence intervals using neural network ensem…

• League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models

  Qianhong Guo, Wei Xie, Xiaofang Cai, Enze Wang, Shuoyoucheng Ma, Xiaobing Sun, Tian Xia, Kai Chen, Xiaofeng Wang, Baosheng Wang · 15. April 2026

  Although large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, reliable evaluation remains a critical challenge due to data contamination, opaque operation, and subjective preferences. To address these issues, we propose League of LLMs (LOL), a novel benchmar…

• SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models

  SungHo Kim, Juhyeong Park, Eda Atalay, SangKeun Lee · 15. April 2026

  Korean is a morphologically rich language with a featural writing system in which each character is systematically composed of subcharacter units known as Jamo. These subcharacters not only determine the visual structure of Korean but also encode frequent and linguistically meaningful morphophonolog…

• Variation in Verification: Understanding Verification Dynamics in Large Language Models

  Yefan Zhou, Austin Xu, Yilun Zhou, Janvijay Singh, Jiang Gui, Shafiq Joty · 15. April 2026

  Recent advances have shown that scaling test-time computation enables large language models (LLMs) to solve increasingly complex problems across diverse domains. One effective paradigm for test-time scaling (TTS) involves LLM generators producing multiple solution candidates, with LLM verifiers asse…

• Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models

  Haonan Yin, Shai Vardi, Vidyanand Choudhary · 15. April 2026

  Large language models (LLMs) are increasingly deployed in decision-support systems for high-stakes domains such as hiring and university admissions, where choices often involve selecting among competing alternatives. While prior work has noted position biases in LLM-driven comparisons, these biases …

• Parcae: Scaling Laws For Stable Looped Language Models

  Hayden Prairie, Zachary Novack, Taylor Berg-Kirkpatrick, Daniel Y. Fu · 15. April 2026

  Traditional fixed-depth architectures scale quality by increasing training FLOPs, typically through increased parameterization, at the expense of a higher memory footprint, or data. A potential alternative is looped architectures, which instead increase FLOPs by sending activations through a block o…

• When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP

  Mahounan Pericles Adjovi, Roald Eiselen, Prasenjit Mitra · 15. April 2026

  Data scarcity limits NLP development for low-resource African languages. We evaluate two data augmentation methods -- LLM-based generation (Gemini 2.5 Flash) and back-translation (NLLB-200) -- for Hausa and Fongbe, two West African languages that differ substantially in LLM generation quality. We as…

• Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series

  Krzysztof Ociepa, {\L}ukasz Flis, Remigiusz Kinas, Krzysztof Wr\'obel, Adrian Gwo\'zdziej · 14. April 2026

  The development of the Bielik v3 PL series, encompassing both the 7B and 11B parameter variants, represents a significant milestone in the field of language-specific large language model (LLM) optimization. While general-purpose models often demonstrate impressive multilingual capabilities, they fre…

• Tuning Language Models for Robust Prediction of Diverse User Behaviors

  Fanjin Meng, Jingtao Ding, Jiahui Gong, Chen Yang, Hong Chen, Zuojian Wang, Haisheng Lu, Yong Li · 14. April 2026

  Predicting user behavior is essential for intelligent assistant services, yet deep learning models often struggle to capture long-tailed behaviors. Large language models (LLMs), with their pretraining on vast corpora containing rich behavioral knowledge, offer promise. However, existing fine-tuning …

• Should We be Pedantic About Reasoning Errors in Machine Translation?

  Calvin Bao, Marine Carpuat · 14. April 2026

  Across multiple language pairings (English $\to$ \{Spanish, French, German, Mandarin, Japanese, Urdu, Cantonese\}), we find reasoning errors in translation. To quantify how often these reasoning errors occur, we leverage an automated annotation protocol for reasoning evaluation wherein the goal is t…

• EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models

  Jinane Bazzi, Mariam Rakka, Fadi Kurdahi, Mohammed E. Fouda, Ahmed Eltawil · 14. April 2026

  The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, and embedded platforms, has exposed fundamental inefficiencies in existing accelerators. While GPUs handle prefill workloads efficiently, the autoregressive decoding phase is dominated by G…

• Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation

  Reza Shirkavand, Xiaokai Wei, Chen Wang, Zheng Hui, Heng Huang, Michelle Gong · 14. April 2026

  While collaborative filtering delivers predictive accuracy and efficiency, and Large Language Models (LLMs) enable expressive and generalizable reasoning, modern recommendation systems must bring these strengths together. Growing user expectations, such as natural-language queries and transparent ex…

• CASK: Core-Aware Selective KV Compression for Reasoning Traces

  Buseong Kim, Heejun Gwon · 14. April 2026

  In large language models performing long-form reasoning, the KV cache grows rapidly with decode length, creating bottlenecks in memory and inference stability. Existing reasoning-oriented KV compression has mostly followed an eviction-centered view: estimate token importance more accurately, then di…

• MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets

  Lai Wei, Xiaozhe Li, Zihao Jiang, Weiran Huang, Lichao Sun · 14. April 2026

  Multimodal large language models are typically trained in two stages: first pre-training on image-text pairs, and then fine-tuning using supervised vision-language instruction data. Recent studies have shown that large language models can achieve satisfactory results even with a limited amount of hi…

• WebLLM: A High-Performance In-Browser LLM Inference Engine

  Charlie F. Ruan, Yucheng Qin, Akaash R. Parthasarathy, Xun Zhou, Ruihang Lai, Hongyi Jin, Yixin Dong, Bohan Hou, Meng-Shiun Yu, Yiyan Zhai, Sudeep Agarwal, Hangrui Cao, Siyuan Feng, Tianqi Chen · 14. April 2026

  Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-grade GPUs and cloud-based inference, the recent emergence of smaller open-source models and increasingly powerful consumer devices have made on-device deploymen…

• The Amazing Agent Race: Strong Tool Users, Weak Navigators

  Zae Myung Kim, Dongseok Lee, Jaehyung Kim, Vipul Raheja, Dongyeop Kang · 14. April 2026

  Existing tool-use benchmarks for LLM agents are overwhelmingly linear: our analysis of six benchmarks shows 55 to 100% of instances are simple chains of 2 to 5 steps. We introduce The Amazing Agent Race (AAR), a benchmark featuring directed acyclic graph (DAG) puzzles (or "legs") with fork-merge too…

• SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

  Talor Abramovich (Izzy), Maor Ashkenazi (Izzy), Carl (Izzy), Putterman, Benjamin Chislett, Tiyasa Mitra, Bita Darvish Rouhani, Ran Zilberstein, Yonatan Geifman · 14. April 2026

  Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and representative workloads are essential for accurately measuring its ef…

• HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks

  Ting Zhou, Daoyuan Chen, Qirui Jiao, Bolin Ding, Yaliang Li, Ying Shen · 14. April 2026

  Evaluating the nuanced human-centric video understanding capabilities of Multimodal Large Language Models (MLLMs) remains a great challenge, as existing benchmarks often overlook the intricacies of emotion, behavior, and cross-modal alignment. We introduce HumanVBench, a comprehensive video benchmar…

• LLM-Rosetta: A Hub-and-Spoke Intermediate Representation for Cross-Provider LLM API Translation

  Peng Ding · 13. April 2026

  The rapid proliferation of Large Language Model (LLM) providers--each exposing proprietary API formats--has created a fragmented ecosystem where applications become tightly coupled to individual vendors. Switching or bridging providers requires $O(N^2)$ bilateral adapters, impeding portability and m…

• Robust Reasoning Benchmark

  Pavel Golikov, Evgenii Opryshko, Gennady Pekhimenko, Mark C. Jeffrey · 13. April 2026

  While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their underlying reasoning processes remain highly overfit to standard textual formatting. We propose a perturbation pipeline consisting of 14 techniques to evaluate robustness of LLM reasoning. We apply…

• The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge

  Gyuwon Park, DongIl Shin, SolGil Oh, SangGi Ryu, Byung-Hak Kim · 13. April 2026

  The rapid evolution of Large Language Models (LLMs) has significantly impacted the field of natural language processing, but their growing complexity raises concerns about resource usage and transparency. Addressing these challenges, we participated in the NeurIPS LLM Efficiency Challenge, aiming to…