Computation and Language

Papers filed under cs.CL on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

1,201 to 1,260 of 11,259

ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification
Jianzong Wang, Chuhang Liu, Botao Zhao +6
cs.CLarXiv:2609.10122v12026
Data-Centric Post-Training for Financial Reasoning: Mining, Distillation, and Verifiable Learning
Zhirayr Hayrapetyan, Andrei Kalmykov, Denis Kokosinskii +2
cs.CLarXiv:2609.10113v12026
Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations
Prashanth Gurunath Shivakumar, Panayiotis Georgiou
eess.AScs.CLcs.SDarXiv:1805.03322v12018
MedDeID enables locally governed clinical-text de-identification from real or synthetic training data
Stig Hellemans, Tom Stroobants, Elyne Scheurwegs +3
cs.CLcs.LGarXiv:2609.10049v12026
Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal
Yunxiang Mo, Donghao Zhao, Hejia Geng
cs.CLarXiv:2609.09989v12026
SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers
Xixian Liao, Maite Melero
cs.CLarXiv:2609.09999v12026
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Ye Tian, Baolin Peng, Linfeng Song +4
cs.CLcs.LGarXiv:2404.12253v22024
Multi-Functional Embedding Models for Funder Name Disambiguation in Scientific Publication Records
Kanyao Han, Zhiwen You, Jinseok Kim +1
cs.CLarXiv:2609.09984v12026
Towards Stress-Aware Sentence-Level Filipino G2P With Weakly-Supervised ByT5 Fine-Tuning
Lorenz Bernard Marqueses, Paulo Grane Gabriel Silva, Chastine Cabatay +2
cs.CLarXiv:2609.09974v12026
Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
Zhuohan Li, Eric Wallace, Sheng Shen +4
cs.CLcs.LGarXiv:2002.11794v22020
$S^3$-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants
Heyang Liu, Jiayi Huang, Wenyang Xiao +8
cs.CLarXiv:2609.09852v12026
HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization
Jianzhi Shen, Keyu Mao, Minghao Shao +7
cs.CLarXiv:2609.09835v12026
Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detection
Lev Konstantinovskiy, Oliver Price, Mevan Babakar +1
cs.CLarXiv:1809.08193v22018
5-Dialects-BN: Unmasking the Impact of Transliteration on Bangla Dialectal LLMs
Md Mahir Jawad, Galib Mahmud Jim, Rafid Ahmed +3
cs.CLarXiv:2609.09964v12026
Contrastive Projection: Reading Transformer Internals by Differencing Logit Lenses
Olli Tuomi
cs.CLarXiv:2609.09902v12026
A Critical Evaluation of Evaluations for Long-form Question Answering
Fangyuan Xu, Yixiao Song, Mohit Iyyer +1
cs.CLarXiv:2305.18201v12023
Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection
Guangxiang Zhao, Junyang Lin, Zhiyuan Zhang +3
cs.CLcs.LGarXiv:1912.11637v12019
Deep and shallow biases in language models
An Vo, Vy Tuong Dang, Khai-Nguyen Nguyen +4
cs.CLarXiv:2609.09901v12026
Large Language Models can Strategically Deceive their Users when Put Under Pressure
Jérémy Scheurer, Mikita Balesni, Marius Hobbhahn
cs.CLcs.AIcs.LGarXiv:2311.07590v42023
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
Carson Denison, Monte MacDiarmid, Fazl Barez +11
cs.AIcs.CLarXiv:2406.10162v32024
Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services
Yonghyun Jun, Jimin Lee, Hwan Chang +3
cs.CLarXiv:2609.09889v12026
When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors
Cho-Ying Wu
cs.CLcs.CYarXiv:2609.09887v12026
The Effect of Natural Distribution Shift on Question Answering Models
John Miller, Karl Krauth, Benjamin Recht +1
cs.LGcs.CLstat.MLarXiv:2004.14444v12020
MUCnoHARM@GermEval Shared Task 2026: Retrieval-based In-Context Learning for Defamatory Offences, and Where It Falls Short
Kristin Gnadt, Maximilian Meidinger, Matthias Aßenmacher
cs.CLarXiv:2609.09791v12026
Iterative Pseudo-Labeling for Speech Recognition
Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn +3
cs.CLcs.SDeess.ASarXiv:2005.09267v22020
ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations
Jianjie Zheng, Peng Lai, Sijie Cheng +3
cs.CLarXiv:2609.09778v12026
Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
Matthias Gerstgrasser, Rylan Schaeffer, Apratim Dey +11
cs.LGcs.AIcs.CLarXiv:2404.01413v22024
SymbolicLight V2: Hybrid Neuromorphic Architecture and Sparse Execution for Low-Energy Language Inference
Ting Liu
cs.CLarXiv:2609.09772v12026
The Self-Perception and Political Biases of ChatGPT
Jérôme Rutinowski, Sven Franke, Jan Endendyk +2
cs.CYcs.AIcs.CLarXiv:2304.07333v12023
Beyond Top Words: MonoTM for Topic Modeling with Interpretable Monosemantic Features
Una Joh, Bei Yu
cs.CLcs.HCarXiv:2609.09575v12026
Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts
Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva +5
cs.CLcs.AIcs.ITarXiv:2306.04723v22023
Eight Methods to Evaluate Robust Unlearning in LLMs
Aengus Lynch, Phillip Guo, Aidan Ewart +2
cs.CLarXiv:2402.16835v12024
CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn Prescription
MinJoo Kim, SanJin Park, SeungHwan Cho
cs.CLarXiv:2609.09766v12026
Towards String-to-Tree Neural Machine Translation
Roee Aharoni, Yoav Goldberg
cs.CLarXiv:1704.04743v32017
MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation
Quan Tu, Yanran Li, Jianwei Cui +3
cs.CLarXiv:2203.13560v22022
StreamAlign: Streaming Text-Aligned Speech Tokenization
Kang-wook Kim, Jinyoung Park, Jinsoo Kim +3
cs.CLcs.SDeess.ASarXiv:2609.09719v12026
Semi-Supervised QA with Generative Domain-Adaptive Nets
Zhilin Yang, Junjie Hu, Ruslan Salakhutdinov +1
cs.CLcs.LGarXiv:1702.02206v22017
SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design
Jianing Wang, Xintao Wang, Aili Chen +7
cs.CLarXiv:2609.09764v12026
Scaling E-Commerce Attribute Extraction with Parallel Decoding
Nikhita Vedula, Dushyanta Dhyani, Bryan Wang +1
cs.CLarXiv:2609.09716v12026
Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases
Boxi Cao, Hongyu Lin, Xianpei Han +5
cs.CLcs.AIarXiv:2106.09231v12021
X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTS
Zehan Liu, Carl Chen, Rime Wen +7
cs.CLarXiv:2609.09677v12026
SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia
Jingyi Liao, Wenyu Zhang, Zhuohan Liu +6
cs.CLarXiv:2609.09672v12026
Probabilistic FastText for Multi-Sense Word Embeddings
Ben Athiwaratkun, Andrew Gordon Wilson, Anima Anandkumar
cs.CLcs.AIcs.LGarXiv:1806.02901v12018
AraGPT2: Pre-Trained Transformer for Arabic Language Generation
Wissam Antoun, Fady Baly, Hazem Hajj
cs.CLarXiv:2012.15520v22020
Reproducing Omitted Temporal Expressions in Japanese News for Retrieval-Augmented Applications
Tomoaki Yasuda, Shotaro Ishihara
cs.CLarXiv:2609.09569v12026
A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta +2
cs.CLcs.AIcs.IRarXiv:2402.09727v32024
Towards Automatic Evolution Tree Generation from Citation Graphs
Zexing Zhao, Yuntong Hu, Liang Zhao
cs.CLarXiv:2609.09561v12026
BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models
Shivam Singh, Aditya Yadavalli, Catherine Arnett +1
cs.CLarXiv:2609.09554v12026
Instruction-driven history-aware policies for robotic manipulations
Pierre-Louis Guhur, Shizhe Chen, Ricardo Garcia +3
cs.ROcs.AIcs.CLarXiv:2209.04899v32022
The Mutations of Machine Speech
Mauricio Figueroa
cs.CLcs.CYcs.HCarXiv:2609.09496v12026
Do LLMs Make More Mistakes If They Do Not Believe the Input Data?
Peter Kochelka, Aleš Manuel Papáček, Vojtěch Dvořák +1
cs.CLarXiv:2609.09363v12026
TEFM: Token-Efficient Faithful Modeling for Structured Data
Zhichao Hou, Lingdao Sha, Xueyu Mao +3
cs.CLcs.LGarXiv:2609.09552v12026
NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions
Rindranirina Ramamonjison, Timothy T. Yu, Raymond Li +8
cs.CLcs.AIarXiv:2303.08233v22023
SciCode: A Research Coding Benchmark Curated by Scientists
Minyang Tian, Luyu Gao, Shizhuo Dylan Zhang +27
cs.AIcs.CLarXiv:2407.13168v12024
Benchmarking Hybrid Deep Research Across Database Querying and Web Search
Ruofan Wu, Peiran Xu, Xiaolong Li +9
cs.CLarXiv:2609.09410v12026
SpecTr: Fast Speculative Decoding via Optimal Transport
Ziteng Sun, Ananda Theertha Suresh, Jae Hun Ro +3
cs.LGcs.CLcs.DSarXiv:2310.15141v22023
SWORD: Wikidata-based Distortions Reveal Hidden Cross-Lingual Inconsistencies in LLM Factual Error Rejection
Sanghyeok Park, Minji Kang, Hosung Kwak +1
cs.CLarXiv:2609.09349v12026
Toward a realistic model of speech processing in the brain with self-supervised learning
Juliette Millet, Charlotte Caucheteux, Pierre Orhan +5
q-bio.NCcs.AIcs.CLarXiv:2206.01685v22022
AMR Parsing as Sequence-to-Graph Transduction
Sheng Zhang, Xutai Ma, Kevin Duh +1
cs.CLarXiv:1905.08704v22019
Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding
Fengxiang Bie, Yuqing Jian, Yifan Yu +7
cs.CLarXiv:2609.09338v12026

Computation and Language

ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification

Data-Centric Post-Training for Financial Reasoning: Mining, Distillation, and Verifiable Learning

Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations

MedDeID enables locally governed clinical-text de-identification from real or synthetic training data

Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal

SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

Multi-Functional Embedding Models for Funder Name Disambiguation in Scientific Publication Records

Towards Stress-Aware Sentence-Level Filipino G2P With Weakly-Supervised ByT5 Fine-Tuning

Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers

$S^3$-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants

HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization

Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detection

5-Dialects-BN: Unmasking the Impact of Transliteration on Bangla Dialectal LLMs

Contrastive Projection: Reading Transformer Internals by Differencing Logit Lenses

A Critical Evaluation of Evaluations for Long-form Question Answering

Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection

Deep and shallow biases in language models

Large Language Models can Strategically Deceive their Users when Put Under Pressure

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services

When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors

The Effect of Natural Distribution Shift on Question Answering Models

MUCnoHARM@GermEval Shared Task 2026: Retrieval-based In-Context Learning for Defamatory Offences, and Where It Falls Short

Iterative Pseudo-Labeling for Speech Recognition

ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations

Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data

SymbolicLight V2: Hybrid Neuromorphic Architecture and Sparse Execution for Low-Energy Language Inference

The Self-Perception and Political Biases of ChatGPT

Beyond Top Words: MonoTM for Topic Modeling with Interpretable Monosemantic Features

Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts

Eight Methods to Evaluate Robust Unlearning in LLMs

CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn Prescription

Towards String-to-Tree Neural Machine Translation

MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation

StreamAlign: Streaming Text-Aligned Speech Tokenization

Semi-Supervised QA with Generative Domain-Adaptive Nets

SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design

Scaling E-Commerce Attribute Extraction with Parallel Decoding

Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases

X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTS

SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia

Probabilistic FastText for Multi-Sense Word Embeddings

AraGPT2: Pre-Trained Transformer for Arabic Language Generation

Reproducing Omitted Temporal Expressions in Japanese News for Retrieval-Augmented Applications

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts

Towards Automatic Evolution Tree Generation from Citation Graphs

BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models

Instruction-driven history-aware policies for robotic manipulations

The Mutations of Machine Speech

Do LLMs Make More Mistakes If They Do Not Believe the Input Data?

TEFM: Token-Efficient Faithful Modeling for Structured Data

NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions

SciCode: A Research Coding Benchmark Curated by Scientists

Benchmarking Hybrid Deep Research Across Database Querying and Web Search

SpecTr: Fast Speculative Decoding via Optimal Transport

SWORD: Wikidata-based Distortions Reveal Hidden Cross-Lingual Inconsistencies in LLM Factual Error Rejection

Toward a realistic model of speech processing in the brain with self-supervised learning

AMR Parsing as Sequence-to-Graph Transduction

Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding