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)

2,101 to 2,160 of 11,247

Adaptive Milestone Reward for GUI Agents
Congmin Zheng, Xiaoyun Mo, Xinbei Ma +10
cs.LGcs.AIcs.CLarXiv:2602.11524v12026
SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
Shenggui Li, Chao Wang, Yikai Zhu +14
cs.LGcs.AIcs.CLarXiv:2603.18567v12026
Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
Jia-Chen Gu, Tianda Li, Quan Liu +4
cs.CLarXiv:2004.03588v22020
Compositionality and Generalization in Emergent Languages
Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt +2
cs.CLcs.AIcs.LGarXiv:2004.09124v12020
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
Muhammad Khalifa, Zohaib Khan, Omer Tafveez +2
cs.LGcs.AIcs.CLarXiv:2603.07084v22026
R2-Router: A New Paradigm for LLM Routing with Reasoning
Jiaqi Xue, Qian Lou, Jiarong Xing +1
cs.CLarXiv:2602.02823v22026
SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking
Hwaran Lee, Jinsik Lee, Tae-Yoon Kim
cs.CLcs.LGarXiv:1907.07421v12019
Deferred Commitment Decoding for Diffusion Language Models
Yingte Shu, Yuchuan Tian, Chao Xu +2
cs.CLcs.AIarXiv:2601.02076v22026
Natural Language Processing for EHR-Based Computational Phenotyping
Zexian Zeng, Yu Deng, Xiaoyu Li +2
cs.CLarXiv:1806.04820v22018
Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models
Wonje Jeung, Sangyeon Yoon, Hyesoo Hong +6
cs.ROcs.CLarXiv:2609.05401v12026
Repeated Queries Exhaust an LLM's Brand Recommendations but Not Its Sources
Dmitrij Żatuchin
cs.IRcs.CLarXiv:2609.05059v12026
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
Naixin Zhai, Pengyang Shao, Binbin Zheng +4
cs.CLarXiv:2601.03190v42026
Current Agents Fail to Leverage World Model as Tool for Foresight
Cheng Qian, Emre Can Acikgoz, Bingxuan Li +8
cs.AIcs.CLcs.LGarXiv:2601.03905v22026
Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
Hongyi Zhou, Jin Zhu, Kai Ye +3
cs.CLcs.AIstat.MLarXiv:2601.21895v22026
Measuring the Novelty of Biomedical Papers Using the Latent Distances between Knowledge Units
Yi Zhao, Heng Zhang, Yuzhuo Wang +3
cs.DLcs.CLarXiv:2609.05175v12026
Large Language Models with At Most One Spike per Neuron
Zhuoya Zhao, Parsa Omidi, Aref Jafari +1
cs.NEcs.CLarXiv:2609.05151v12026
FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search
James Xu Zhao, Hui Chen, Bryan Hooi +1
cs.CLarXiv:2606.00660v22026
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
Janghyeon Kim, Minsoo Kim, Kyuhong Shim +1
cs.LGcs.CLarXiv:2609.04971v12026
Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference
Tim Wientzek
cs.CLarXiv:2609.05262v12026
Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers
Yumiao Li, Peixin Liu, Donglin Di +2
cs.CLarXiv:2609.05189v12026
Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG
Shuyu Guo, Shuo Zhang, Zhaochun Ren
cs.CLarXiv:2609.05152v12026
From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making
Davide Testa, Hugh Mee Wong, Alessandro Lenci +2
cs.CLcs.CVarXiv:2609.05149v12026
Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
Yanchen Wu, Tenghui Lin, Yingli Zhou +7
cs.CLcs.DBarXiv:2604.01707v32026
Retinal OCTA Phenotyping with LLM Reporting for Alzheimer's Disease
Progga Paromita Dutta, Jeba Maliha, Md Rafiul Kabir
cs.CVcs.CLarXiv:2609.04689v12026
Latent-Aligned Reasoning for Multimodal Recommendation
Jiarui Jin, Anyang Ji
cs.IRcs.CLcs.CVarXiv:2609.04645v12026
JLIR: A Julia-Native MLIR-Inspired Intermediate Representation with Automatic JACC Kernel Extraction
Narasinga Rao Miniskar, Seyong Lee, Keita Teranishi +1
cs.PLcs.CLarXiv:2609.04585v12026
WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data
Ji Soo Lee, Xilun Chen, Pierce Chuang +5
cs.CLarXiv:2609.05405v12026
LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics
Gaurab Baral
cs.CLcs.LGarXiv:2609.05296v12026
LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards
Bowen Ping, Zijun Chen, Yiyao Yu +3
cs.CLarXiv:2602.05758v12026
Massive Sound Embedding Benchmark (MSEB)
Georg Heigold, Ehsan Variani, Tom Bagby +4
cs.SDcs.CLarXiv:2602.07143v12026
Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks
Yonatan Belinkov, Lluís Màrquez, Hassan Sajjad +3
cs.CLarXiv:1801.07772v12018
Physically Interpretable AlphaEarth Foundation Model Embeddings Enable LLM-Based Land Surface Intelligence
Mashrekur Rahman
cs.CLcs.LGarXiv:2602.10354v12026
Improving Language Identification for Code-Switched Utterances with Integer Linear Programming
Joanna Radoła, Josep Maria Crego, François Yvon
cs.CLarXiv:2609.05099v12026
EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages
Aleix Sant, Jordi Luque, Carlos Escolano
cs.CLarXiv:2609.05043v12026
FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions
Peng Li, Zihan Zhuang, Yangfan Gao +16
cs.ROcs.CLcs.CVarXiv:2601.12799v12026
Generative Adversarial Network for Abstractive Text Summarization
Linqing Liu, Yao Lu, Min Yang +3
cs.CLcs.AIarXiv:1711.09357v12017
COMI: Coarse-to-fine Context Compression via Marginal Information Gain
Jiwei Tang, Shilei Liu, Zhicheng Zhang +4
cs.CLarXiv:2602.01719v32026
NS-ST-GraphRAG: Neuro-Symbolic Spatio-Temporal GraphRAG for Literary Knowledge Processing
Zheng Kui Lin
cs.CLarXiv:2609.05139v12026
Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty
Sravanthi Machcha, Sushrita Yerra, Sahil Gupta +4
cs.CLcs.AIarXiv:2601.12471v22026
Influence Score and Transformers interpretability: Measure of the Effective Impact of Attention Heads at inference time
Lisa Bouger, Yannick Teglia, Philippe Loubet Moundi
cs.CLarXiv:2609.05074v12026
ChatGPT: A Meta-Analysis after 2.5 Months
Christoph Leiter, Ran Zhang, Yanran Chen +4
cs.CLarXiv:2302.13795v12023
MoirfEolas and CríochScore: Developing Resources for and the Evaluation of Tokenization Alignment with Irish Morphology
Jane Adkins, Abigail Walsh, Brian Davis +1
cs.CLarXiv:2609.05022v12026
Attend to You: Personalized Image Captioning with Context Sequence Memory Networks
Cesc Chunseong Park, Byeongchang Kim, Gunhee Kim
cs.CVcs.CLarXiv:1704.06485v22017
Discourse Dependency: A Continuous Criterion for Translation Difficulty
Ahrii Kim, Chanjun Park, Seong-heum Kim
cs.CLarXiv:2609.04959v12026
BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer Generation
André Ribeiro, Rúben Garrido, Alexander Christiansen +2
cs.CLarXiv:2609.04999v12026
Scalable Training of Mixture-of-Experts Models with Megatron Core
Zijie Yan, Hongxiao Bai, Xin Yao +42
cs.DCcs.CLcs.LGarXiv:2603.07685v22026
Do We Still Need Clinical Language Models?
Eric Lehman, Evan Hernandez, Diwakar Mahajan +7
cs.CLarXiv:2302.08091v12023
Cache-Aware Joint Router Adaptation for Memory-Efficient MoE Inference
Zhenhe Wu, Yaping Jin, Qinghua Xing +6
cs.CLarXiv:2609.04895v12026
On Epistemic Diversity in Large Language Models
Elisabeth Kirsten, Nicole Krämer, Muhammad Bilal Zafar
cs.CLarXiv:2609.04835v12026
Open Sesame! Universal Black Box Jailbreaking of Large Language Models
Raz Lapid, Ron Langberg, Moshe Sipper
cs.CLcs.CVcs.NEarXiv:2309.01446v42023
Task-Oriented Dialogue as Dataflow Synthesis
Semantic Machines, Jacob Andreas, John Bufe +43
cs.CLarXiv:2009.11423v32020
Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue Generation
Jongkyung Shin, Inkyu Lee, Chiehyeon Lim
cs.CLarXiv:2609.04676v12026
MedDialogRubrics: A Comprehensive Benchmark and Evaluation Framework for Multi-turn Medical Consultations in Large Language Models
Lecheng Gong, Weimin Fang, Ting Yang +9
cs.CLcs.HCarXiv:2601.03023v22026
Generating Constructive Feedback on Stories via Reinforcement Learning
Maja Stahl, Timon Ziegenbein, Henning Wachsmuth
cs.CLarXiv:2609.04824v12026
If beam search is the answer, what was the question?
Clara Meister, Tim Vieira, Ryan Cotterell
cs.CLarXiv:2010.02650v22020
Learning to Self-Verify Makes Language Models Better Reasoners
Yuxin Chen, Yu Wang, Yi Zhang +9
cs.CLcs.AIarXiv:2602.07594v12026
A Systematic Comparison of Multilingual Interpretability Methods Reveals Anisotropy-Driven Failures
Oskar Holmström, Marcel Bollmann, Marco Kuhlmann
cs.CLarXiv:2609.04819v12026
A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data
Yinhe Zheng, Rongsheng Zhang, Xiaoxi Mao +1
cs.CLcs.AIcs.LGarXiv:1911.04700v12019
Vectorizing Classical Tamil: Representation Learning for Verse-Commentary Pairs
Amrit Gopinath, Sangeetha Sivanesan
cs.CLarXiv:2609.04755v12026
Prompt-Learning for Fine-Grained Entity Typing
Ning Ding, Yulin Chen, Xu Han +6
cs.CLcs.AIarXiv:2108.10604v12021

Computation and Language

Adaptive Milestone Reward for GUI Agents

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding

Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots

Compositionality and Generalization in Emergent Languages

Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR

R2-Router: A New Paradigm for LLM Routing with Reasoning

SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking

Deferred Commitment Decoding for Diffusion Language Models

Natural Language Processing for EHR-Based Computational Phenotyping

Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models

Repeated Queries Exhaust an LLM's Brand Recommendations but Not Its Sources

Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning

Current Agents Fail to Leverage World Model as Tool for Foresight

Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text

Measuring the Novelty of Biomedical Papers Using the Latent Distances between Knowledge Units

Large Language Models with At Most One Spike per Neuron

FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference

Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers

Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG

From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making

Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework

Retinal OCTA Phenotyping with LLM Reporting for Alzheimer's Disease

Latent-Aligned Reasoning for Multimodal Recommendation

JLIR: A Julia-Native MLIR-Inspired Intermediate Representation with Automatic JACC Kernel Extraction

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

Massive Sound Embedding Benchmark (MSEB)

Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks

Physically Interpretable AlphaEarth Foundation Model Embeddings Enable LLM-Based Land Surface Intelligence

Improving Language Identification for Code-Switched Utterances with Integer Linear Programming

EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages

FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

Generative Adversarial Network for Abstractive Text Summarization

COMI: Coarse-to-fine Context Compression via Marginal Information Gain

NS-ST-GraphRAG: Neuro-Symbolic Spatio-Temporal GraphRAG for Literary Knowledge Processing

Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty

Influence Score and Transformers interpretability: Measure of the Effective Impact of Attention Heads at inference time

ChatGPT: A Meta-Analysis after 2.5 Months

MoirfEolas and CríochScore: Developing Resources for and the Evaluation of Tokenization Alignment with Irish Morphology

Attend to You: Personalized Image Captioning with Context Sequence Memory Networks

Discourse Dependency: A Continuous Criterion for Translation Difficulty

BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer Generation

Scalable Training of Mixture-of-Experts Models with Megatron Core

Do We Still Need Clinical Language Models?

Cache-Aware Joint Router Adaptation for Memory-Efficient MoE Inference

On Epistemic Diversity in Large Language Models

Open Sesame! Universal Black Box Jailbreaking of Large Language Models

Task-Oriented Dialogue as Dataflow Synthesis

Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue Generation

MedDialogRubrics: A Comprehensive Benchmark and Evaluation Framework for Multi-turn Medical Consultations in Large Language Models

Generating Constructive Feedback on Stories via Reinforcement Learning

If beam search is the answer, what was the question?

Learning to Self-Verify Makes Language Models Better Reasoners

A Systematic Comparison of Multilingual Interpretability Methods Reveals Anisotropy-Driven Failures

A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data

Vectorizing Classical Tamil: Representation Learning for Verse-Commentary Pairs

Prompt-Learning for Fine-Grained Entity Typing