Natural language processing

Classical and neural NLP: translation, question answering, tokenization and the evaluation of language understanding.

2,601 stories · RSS feed

arXiv AI

Sep 7

MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis

MedFlow is a class‑aware multi‑scale flow matching framework designed to synthesize medical time‑series data. It uses a vector‑quantized multi‑scale tokenizer to capture both coarse and fine temporal patterns, and introduces Token Marginal Guidance to steer generation toward minority‑class characteristics. Experiments on four public datasets show MedFlow outperforms diffusion baselines, improving AUPRC by 5.8%, reducing Context‑FID by 88.6%, and achieving 3.8× higher sampling throughput.

By Yanhao Huang, Shibo Feng, Wanjin Feng, Peilin Zhao, Chunyan Miao

diffusion nlp efficiency benchmarks

arXiv Computation and Language

Sep 7

Cross-Preference Learning for Sentence-Level and Context-Aware Machine Translation

The paper introduces Cross-Preference Learning (CPL), a training framework that explicitly models the complementary strengths of sentence-level and context-aware machine translation. By incorporating intra- and cross-condition preferences into the optimization objective, CPL provides targeted supervision to leverage useful contextual signals while remaining robust to uninformative context. Experiments on multiple public context-aware MT tasks with models such as Qwen3-4B, Qwen3-8B, and Llama-3-8B-Instruct show consistent improvements in translation quality and robustness without altering the model architecture.

By Ying Li, Xinglin Lyu, Junhui Li, Jinlong Yang, Hengchao Shang, Min Zhang, Shimin Tao, Daimeng Wei

llms nlp

arXiv Machine Learning

Sep 7

Consensus Group Relative Policy Optimization for Text Generation

Consensus Group Relative Policy Optimization (C‑GRPO) is a new training method that distills Minimum Bayes Risk (MBR) decoding into a group‑relative objective, enabling text generation models to approximate MBR performance without the costly inference‑time sampling and scoring. C‑GRPO only needs a utility function and policy samples, avoiding the need for gold references or curated preference data. Experiments on WMT 2024 machine translation and XSum summarization show that C‑GRPO matches MBR decoding quality while reducing inference overhead and outperforming other reference‑free baselines.

By Yuki Ichihara, Yuu Jinnai, Kaito Ariu, Eiji Uchibe

nlp

arXiv AI

Sep 7

Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization

The paper introduces CAMS, a Claim‑Anchored Multi‑Document Summarization framework that decomposes source documents into atomic claims, resolves provenance deterministically from verbatim quotes to token spans, clusters equivalent claims across documents, and rewrites summaries so each sentence ends with claim identifiers linking back to source spans. CAMS separates provenance (an invariant for each emitted sentence) from faithfulness (an objective encouraged by selection, rewriting, and verification). Evaluations on MultiNews, DiverseSumm, and zero‑shot WCEP show that CAMS matches strong baselines in summary quality while improving faithfulness and citation precision, raising attribution accuracy from 38% to 64% and reducing human verification time per claim by 3.4×.

By Shuo Guan

llms nlp

arXiv AI

Sep 7

A Verifier-Guided Explainable Reasoning Framework with Gold-Anchored QLoRA, Task-Aware Mixture-of-Experts, and Group-Relative RLVR

The paper introduces a verifier‑guided explainable reasoning framework for educational question answering that integrates gold‑anchored QLoRA, a task‑aware symbolic router, and group‑relative RLVR. It adapts Qwen2.5‑3B‑Instruct with field‑weighted QLoRA supervision, routes logic problems to a FOL/Z3 verifier and physics problems to a symbolic solver, and uses verifier feedback for candidate evaluation, self‑revision, and reward construction. Experiments on 438 held‑out examples show that RLVR boosts reasoning depth (P3) from 50.68 % to 72.20 %, while symbolic verification improves answer reliability at the system level.

By Thi Kim Trang Vo, Nam Tien Le, Thi Kim Nguyet Vo, Minh Khang Tran, Duy Phuong Tran

llms nlp fine-tuning

Hugging Face Trending Papers

Sep 6

A Novel Semantic Manifold Alignment Attack against Embedding-to-Embedding Obfuscation in Privacy-Preserving LLMs

With the widespread applications of large language models (LLMs), privacy-preserving inference has become increasingly essential for sensitive queries. To balance privacy and utility, a series of ligh...

llms rag nlp benchmarks safety

Hugging Face Trending Papers

Sep 6

Discovering Translation-Worthy Languages with E-Values

Choosing when to translate multilingual documents is a central routing problem in text classification: translation can improve predictions for some languages while degrading others or adding unnecessa...

nlp

arXiv Computation and Language

Sep 4

Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models

The paper evaluates large language models (LLMs) on Arabic morphosyntactic tagging and dependency parsing, a challenging task due to rich morphology and orthographic ambiguity. It compares zero‑shot prompting with retrieval‑based in‑context learning across pre‑tokenized, raw‑text, and cascaded settings, finding that relevant demonstrations significantly boost performance. The best LLMs nearly match supervised systems but need extensive annotated data for demonstrations and high computational resources. All code and data are publicly released.

By Mohamed Adel, Bashar Alhafni, Nizar Habash

llms nlp

arXiv Computer Vision

Sep 4

Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving

The paper introduces LaPla, a Vision‑Language‑Action framework that uses a latent‑aligned planning approach to convert discrete semantic reasoning into continuous, physics‑constrained driving actions. It employs a residual VQ‑VAE to encode vehicle kinematics into a structured latent space, then projects multimodal inputs—images, past actions, and text—directly into this latent space, allowing a frozen decoder to generate physically plausible trajectories without quantization errors. Experiments on nuScenes and NVIDIA AlpaSim show LaPla reduces long‑horizon L2 error by 15.52% and improves closed‑loop success rates by 33.34 percentage points while cutting inference latency.

By Ruoyu Yao, Yusen Xie, Qingzhao Liu, Pei Liu, Zewei Yang, Yipeng Zhu, Xiaolong Wang, Jun Ma

llms agents diffusion nlp robotics efficiency multimodal benchmarks

arXiv Computation and Language

Sep 4

Detecting Conversational Mental Manipulation with Intent-Aware Prompting

The paper introduces Intent‑Aware Prompting (IAP), a new method that uses large language models to detect mental manipulation in conversations by identifying the underlying intents of participants. Experiments on the MentalManip dataset show that IAP outperforms other prompting strategies, especially by reducing false negatives and improving detection of subtle manipulative tactics. The authors provide the code for reproducibility.

By Jiayuan Ma, Hongbin Na, Zimu Wang, Yining Hua, Yue Liu, Wei Wang, Ling Chen

llms nlp robotics

arXiv AI

Sep 4

ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize

ESPO (Error-Structured Prompt Optimization) addresses prompt bloat in evolutionary prompt optimizers by splitting the optimization process into Diagnose, Propose, and Select phases. It clusters training errors into structural patterns, generates diverse candidate prompts through four complementary strategies, and applies bootstrap stability selection. Across seven NLP benchmarks, ESPO improves average accuracy by +3.76 pp over GEPA, produces prompts 47 % shorter, and achieves higher accuracy on four additional student models, with the largest gain on Qwen3 GSM8K.

By Lihao Liu, Peng Tang, Kunwar Yashraj Singh, Shabnam Ghadar

llms nlp benchmarks

arXiv Computation and Language

Sep 4

Evaluating Large Language Models on Urdu Idioms

The paper introduces a new benchmark for Urdu‑to‑English idiomatic translation, featuring 4,000 manually verified sentence pairs in both native Perso‑Arabic script and Romanized Urdu. It evaluates multiple tasks—translation, paraphrasing, idiom span detection, and back‑translation—using various prompting strategies, and finds that state‑of‑the‑art large language models outperform traditional neural machine translation systems, especially in preserving figurative meaning. The study also highlights challenges posed by the lack of standardized orthography in Romanized Urdu, which affects consistency and idiom span detection.

By Muhammad Farmal Khan, Mousumi Akter

llms nlp benchmarks

arXiv AI

Sep 4

One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging

The paper investigates weight‑space merging of independently fine‑tuned multilingual machine translation models. Experiments show that merging is more successful when models share a target language, yet it still cannot match the peak performance of language‑specific checkpoints. When target languages differ, performance drops sharply, and analysis reveals that overlapping neuron activation and incompatible upper‑layer geometries cause these failures.

By Baban Gain, Trilok Nath Singh, Asif Ekbal

llms nlp fine-tuning

arXiv Computer Vision

Sep 4

M3T: Discrete Multi-Modal Motion Tokens for Sign Language Production

M3T introduces a discrete multi‑modal motion token system for sign language production, addressing the need for non‑manual features such as mouthings, eyebrow raises, gaze, and head movements. The approach couples FLAME’s expressive facial space with SMPL‑X body parameters and uses modality‑specific Finite Scalar Quantization VAEs to achieve high face codebook utilization (99.0%). Trained with an autoregressive transformer and a sign‑to‑text translation objective, M3T outperforms existing methods on three standard datasets, notably improving accuracy on NMFs‑CSL from 49.0% to 58.3% without large‑scale pre‑training.

By Alexandre Symeonidis-Herzig, Jianhe Low, Ozge Mercanoglu Sincan, Richard Bowden

llms rag nlp efficiency multimodal benchmarks

arXiv Computation and Language

Sep 4

The Impact of Synthetic Data Augmentation on Discourse-Pragmatic Function Classification

The study examines how the geometric placement of synthetic data affects discourse‑pragmatic function classification. Using 410 annotated instances of the word "look" from the British National Corpus, synthetic examples were generated with Llama 3.1 and grouped by cosine distance from real data in RoBERTa space. Six training conditions were compared, showing that examples close to real data (NEAR) yield the largest macro‑F gain, while a distance‑balanced mix gives the highest accuracy, yet none improve AUC.

By Sara Sorahi, Kevin Tang, Reza Kazemian

llms rag nlp efficiency

arXiv Computation and Language

Sep 4

Last Translation Benchmark

The paper introduces the Last Translation Benchmark (LTB), a live dataset of human-authored and peer‑reviewed examples—including texts, images, audio, and videos—that are designed to break current state‑of‑the‑art machine translation models. Each example is accompanied by handcrafted verification rules that specify concrete failure cases, providing a reliable and actionable evaluation method. The benchmark aims to overcome the limitations of existing automatic metrics and gold human evaluations, which often lack reproducibility, objectivity, and scalability.

By Vil\'em Zouhar, Niyati Bafna, Mukund Choudhary, Maike Z\"ufle, Sara Rajaee, Pinzhen Chen, Jannis Vamvas, Sara Papi, Ona de Gibert, Bhavitvya Malik, Eliya Habba, Orfeas Menis Mastromichalakis, Patr\'icia Schmidtov\'a, Michelle Wastl, Sheriff Issaka, Leshem Choshen, Stella Biderman, Antonis Anastasopoulos, Jan Niehues, Rico Sennrich, Mrinmaya Sachan, Ond\v{r}ej Bojar, Kenton Murray, J\"org Tiedemann, Alham Fikri Aji, Philipp Koehn, Christof Monz, Alexandra Birch, Sowmya Vajjala, Chalamalasetti Kranti, Cristina Espa\~na-Bonet, Nobin Sarwar, David Kacz\'er, Shunta Asano, Malik Marmonier, Daban Q. Jaff, Vaisakhi Mishra, Hend Al- Khalifa, Gabriele Sarti, Sourajit Saha, Nils Rehlinger, Juan Daniel Cuervo Villa, Jonathan Tonglet, Saugata Purkayastha, Dominik Mach\'a\v{c}ek, Jagannathan Ramanujam, Heejin Do, Zuzana Nadova, Fred Philippy, Fabian Retkowski, Maria Lymperaiou, Silvia Casola, Hanna Yukhymenko, Shubhashis Roy Dipta, Sangwon Ryu, Andr\'es Jerez, Ron Keinan, Shuaib Shuaib Yusuf, Avantica Vempati, Maria Carmen Staiano, Sukannya Purkayastha, Adrian Cosma, Vitalii Babenko, Erivan Inan, Aviral Nigam, Wafa Aissa, Fatima Haouari, Venkata Prasanth Kumar Gummadi, Mehdi Jafarzadeh, Valentin Scourneau, Lukas Edman, Kaiser Sun, Shaomu Tan, Mohammad Sadegh Gholizadeh, Johannes-Rudolf David, Dipankar Srirag, Javier Garc\'ia Gilabert, Ruta Binkyte, Manar Ali, Ana-Maria Bucur, Sabry E. Farrag, Youssef Saber, Yihong Liu, Jean Maillard, Cojocaru Nicoleta, Xiaochuang Yuan, Sina Ahmadi, Philipp Mondorf, Kaustubh Dhole, Roman Wixinger, Shenbin Qian, Manuel Tuor, Sergey Troshin, Jonathan Yahav, Fida Mohammad Thoker, Amir Arsalan Rezapour, Lance Calvin Lim Gamboa, Manon Reusens, K\"atriin Kukk, Koel Dutta Chowdhury, Giuseppe Gallipoli, Christian Hoang, Shaswati Saha, Seth Aycock, Jan Koco\'n, Bo Chen, Linh Vu, Vatsal Venkatkrishna, Arafat Ahsan, Luan Thanh Nguyen, Hassan Soliman, Daryna Dementieva, Theresia Veronika Rampisela, Ngoc Quynh Tram Do, Marius Huber, Kazuki Egashira, Azmine Toushik Wasi, Vladislav Poritski, Mike Zhang, Deep Shah, Paul Gavrikov, Luis Frentzen Salim, David Africa, R. Damanhuri, Bello Umar Bello, Anumit Garg, Gengyu Rao, Pawan Sasanka Ammanamanchi, Kamile Dementaviciute, Andrianos Michail, L D M S Sai Teja, Dawei Zhu, Yi Fan, Wei Liu, Farhan Farsi, Elias Herranen, Sankalan Pal Chowdhury, Karen Sanchez, Farzad Shami, Ashok Urlana, Zimu Wang, Tomasz Limisiewicz, Priyaranjan Pattnayak, Marii Ojastu, Hongbin Na, Emilian Radoi, Chenyi Zhao, Carlos Hinojosa, Andrea Gregor de Varda, Zaid Alyafeai, Reem Alzahrani, Nehal Kathrotia, Alex Fl\"uckiger, Ulysses Sekai Tully Carr, Jimson Paulo Layacan, Guy Kaplan, Ritwik Tiwari, Rishit Dagli, Oksana Volchek, Isaac R Caswell, Bowen Yi, Blanka K\"ov\'er, Amir Hossein Yari, Aicha Chorana, Zhengxiang Wang, Selja Ker\"anen, Samuel Simko, Joy Olusanya, Jenny Chim, Enzo Doyen, Vivek Harsha Lakkamaneni, Sophia Conrad, Pouya Sadeghi, Panayiotis Panayiotou, Luis Lara, Jannatul Nayem, Eran Yahav, Debanshu Das, Antonia Karamolegkou, Anmol Goel, Aishik Mandal, Tommaso Cerruti, Raoyuan Zhao, Mykola Haltiuk, Thura Aung, Naser Almousa, Amir Hossein Kargaran, Rachel Bawden, Qiaoyuan Zheng, Mateusz Lango, Beni Egressy, Fidel Rodr\'iguez Vel\'asquez, Natchapon Jongwiriyanurak, Minh Ngoc Do, Marco Gaido, Lena Libon, Dzmitry Kuzmin, Badal Nyalang, Antoine Taroni, Andrei Niculae, Abdulaziz Nura Kani, Rushikesh Zawar, Marek \v{S}uppa, Beatrice Savoldi, Andreas Simons, Rayyan Merchant, Ilai Yaron Levy, Francesco Pinto, Ziyi Yang, Yolanda Xavier, Samuel Frontull, Muhammad Ravi Shulthan Habibi, Kenneth Enevoldsen, Harris Abdul Majid, Francesca Padovani, Tim Graf, Tatiana Bielakova, Sharifa Djurabaeva, Shaoxiong Ji, Raia Abu Ahmad, Pavel Stepachev, Jirui Qi, Ayush Sunil Munot, Alireza Pakniat, Ayla Rigouts Terryn, Yuxing Lu, Yurii Paniv, Xiyan Fu, Tosin Adewumi, Sunisth Kumar, St\'ephane J. P. S. Thunus, Shree Harsha Bokkahalli Satish, Shayan Bali, Prakhar Gupta, Papa Abdou Karim Karou Diallo, Matija Akrap, Marko Culjak, Krist\'yna Onderkov\'a, Joseph Attieh, Esrael Teferi Tensay, Elisabeth Fittschen, Beno\^it Sagot, Jingwei Ni, Yu Fan

nlp benchmarks

arXiv Machine Learning

Sep 4

Unifying Conformal Language Tasks with In-Context Ensembles

The paper introduces the Conformal Relevance framework, which employs in-context learning example curation and ensembling to generate a score function that preserves coverage while enhancing conciseness for NLP tasks such as summarization and extractive question answering. Unlike previous methods that rely on labor-intensive, task‑specific prompt engineering, this approach requires minimal manual input. The authors validate the framework across seven NLP tasks and provide a theoretical analysis of how diversity in ensembled conformal scores can improve worst‑case sentence scores, including a saturation bound on ensemble gains.

By Xiao Shi Huang, Chen-Yuan Lin, Bruce Kuwahara, Kin Kwan Leung, Jesse C. Cresswell

llms nlp benchmarks

arXiv AI

Sep 4

A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant

The paper introduces a prompt‑engineering framework that personalizes large language model (LLM) teaching assistants across disciplines by tailoring responses to six learner‑specific dimensions, creating 96 distinct learner profiles. It also analyzes student queries through Bloom’s Taxonomy to gauge cognitive complexity, encoding both learner attributes and cognitive assessments into structured prompts that condition the LLM without retraining. Experiments using NLP metrics and a small human study demonstrate that this approach yields perceptible differences in response style and structure, with statistical evidence linking specific learner attributes to measurable changes.

By Saptarshi Basu, Sandeep Kakar, Ashok Goel

llms rag agents nlp

arXiv Computation and Language

Sep 4

Benchmarking Machine Translation on Chinese Social Media Texts

The paper introduces CSM-MTBench, a benchmark for evaluating machine translation on Chinese social media text. It addresses two main challenges: limited parallel data due to slang and stylistic nuances, and inadequate evaluation metrics that miss these informal features. The benchmark includes two expert-curated subsets—Fun Posts and Social Snippets—and proposes specialized evaluation methods for each, revealing significant differences among over 20 MT models in handling semantic and stylistic aspects.

By Kaiyan Zhao, Zheyong Xie, Zhongtao Miao, Xinze Lyu, Yao Hu, Shaosheng Cao

llms rag nlp benchmarks

arXiv Computation and Language

Sep 4

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG

The paper introduces Causal-Counterfactual RAG, a new framework that augments Retrieval-Augmented Generation with explicit causal graphs and counterfactual reasoning. By incorporating cause‑effect relationships into retrieval and evaluating both direct causal evidence and counterfactual scenarios, the approach aims to produce more robust, accurate, and interpretable answers. This method seeks to maintain contextual coherence, reduce hallucinations, and improve reasoning fidelity compared to traditional RAG systems.

By Harshad Khadilkar, Abhay Gupta

llms rag nlp safety

Get the daily briefing