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)

1,261 to 1,320 of 11,244

GANDR: Claim Auditing for Verifiable Legal Answer Generation
Chen Qian, Yimeng Wang, Yu Chen +2
cs.CLcs.AIcs.IRarXiv:2609.10293v12026
DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs
Bhuvan Arora, Devesh Saraogi, Sravya Varada +1
cs.CLcs.AIarXiv:2609.10253v12026
LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation
Daniel Alejandro Coll Tejeda, Pedro García López, Daniel Barcelona-Pons
cs.IRcs.AIcs.CLarXiv:2609.10239v12026
GenSim: Generating Robotic Simulation Tasks via Large Language Models
Lirui Wang, Yiyang Ling, Zhecheng Yuan +6
cs.LGcs.CLcs.CVarXiv:2310.01361v22023
Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning
Jing Guan, Yachao Yang, Zhaoliang Liu +3
cs.CLcs.AIcs.CRarXiv:2609.10142v12026
Weak Supervision for Fake News Detection via Reinforcement Learning
Yaqing Wang, Weifeng Yang, Fenglong Ma +4
cs.SIcs.CLcs.LGarXiv:1912.12520v22019
Evaluating the Factual Consistency of Large Language Models Through News Summarization
Derek Tam, Anisha Mascarenhas, Shiyue Zhang +3
cs.CLarXiv:2211.08412v22022
Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning
Nagham Omar, Maya Rozenshtein, Evgeny Mishlyakov +1
cs.LGcs.CLarXiv:2609.06806v12026
Affective Neural Response Generation
Nabiha Asghar, Pascal Poupart, Jesse Hoey +2
cs.CLcs.AIcs.CYarXiv:1709.03968v12017
End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
Jason D. Williams, Geoffrey Zweig
cs.CLcs.AIcs.LGarXiv:1606.01269v12016
Toward Gender-Inclusive Coreference Resolution
Yang Trista Cao, Hal Daumé
cs.CLarXiv:1910.13913v42019
NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environments
Niramay M. Patel, Bibek Behera, Raksha Sharma
cs.SDcs.AIcs.CLarXiv:2609.10058v12026
Does Gender Matter? Towards Fairness in Dialogue Systems
Haochen Liu, Jamell Dacon, Wenqi Fan +3
cs.CLcs.AIarXiv:1910.10486v32019
Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training
Junwon Ko, Dong-Jae Lee, Minchan Kwon +2
cs.CLcs.AIcs.LGarXiv:2609.10052v12026
MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes
Remco Hendriks
cs.LGcs.AIcs.CLarXiv:2609.10016v12026
Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture
Jiaxi Cui, Munan Ning, Zongjian Li +6
cs.CLarXiv:2306.16092v32023
Improving Cross-Lingual Token Representations by Adding a Pinch of SALT
Guillem Ramírez
cs.CLcs.AIarXiv:2609.09953v12026
OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples
Ryuto Koike, Masahiro Kaneko, Naoaki Okazaki
cs.CLarXiv:2307.11729v32023
Strangers to Themselves: What Language Models Say About Themselves Is Generic
Phil Blandfort, Urja Pawar
cs.LGcs.AIcs.CLarXiv:2609.09899v12026
DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction
Pengda Qin, Weiran Xu, William Yang Wang
cs.CLarXiv:1805.09929v12018
From Audio to Semantics: Approaches to end-to-end spoken language understanding
Parisa Haghani, Arun Narayanan, Michiel Bacchiani +6
eess.AScs.CLcs.SDarXiv:1809.09190v12018
Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?
Fumihiko Tachibana, Daisuke Miyashita, Jun Deguchi
cs.LGcs.AIcs.CLarXiv:2609.09768v12026
deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
Michel Galley, Chris Brockett, Alessandro Sordoni +6
cs.CLarXiv:1506.06863v22015
How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE
Yi Shi, Tanyu Chen, Kai Shen
cs.CRcs.AIcs.CLarXiv:2609.09793v12026
LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial Scenarios
Hanjing Zhou, Mingze Yin, Ying Lian +3
cs.CVcs.AIcs.CLarXiv:2609.09790v12026
Advancing Multimodal Medical Capabilities of Gemini
Lin Yang, Shawn Xu, Andrew Sellergren +44
cs.CVcs.AIcs.CLarXiv:2405.03162v12024
Probing the Need for Visual Context in Multimodal Machine Translation
Ozan Caglayan, Pranava Madhyastha, Lucia Specia +1
cs.CLarXiv:1903.08678v22019
Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification
Binxuan Huang, Kathleen M. Carley
cs.CLarXiv:1909.06276v12019
Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs
Houyu Zhang, Zhenghao Liu, Chenyan Xiong +1
cs.CLcs.AIarXiv:1911.02707v32019
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
Hu Xu, Gargi Ghosh, Po-Yao Huang +5
cs.CVcs.CLarXiv:2105.09996v32021
Intra-Prompt Parallel Decoding for Common-Context Question Answering
Theodore Glavas, Nikhita Vedula, Dushyanta Dhyani +3
cs.CLarXiv:2609.05707v12026
Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling
Tingshuo Fan, Hongtao Mu, Tianyu Zhou +2
cs.CLcs.AIarXiv:2609.09691v12026
A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis
Shai Gretz, Roni Friedman, Edo Cohen-Karlik +4
cs.CLarXiv:1911.11408v12019
To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection
Aparna Balagopalan, Benjamin Eyre, Frank Rudzicz +1
cs.CLcs.LGarXiv:2008.01551v12020
Fastformer: Additive Attention Can Be All You Need
Chuhan Wu, Fangzhao Wu, Tao Qi +2
cs.CLarXiv:2108.09084v62021
OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
Keiran Paster, Marco Dos Santos, Zhangir Azerbayev +1
cs.AIcs.CLcs.LGarXiv:2310.06786v12023
When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination
Karan Parekh, Sanjana Pendyala Ravinder, Sana Mhapsekar +1
cs.CLcs.AIarXiv:2609.09696v12026
SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness
Nathan Ng, Kyunghyun Cho, Marzyeh Ghassemi
cs.CLcs.LGstat.MLarXiv:2009.10195v22020
Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA
Yuexin Wu, Dayou Yu, Vasile Rus
cs.CLcs.AIarXiv:2609.09684v12026
Towards Improving Adversarial Training of NLP Models
Jin Yong Yoo, Yanjun Qi
cs.CLcs.AIcs.LGarXiv:2109.00544v22021
ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
Zhanqiu Zhang, Jie Wang, Jiajun Chen +2
cs.AIcs.CLarXiv:2110.13715v22021
SemEval-2023 Task 10: Explainable Detection of Online Sexism
Hannah Rose Kirk, Wenjie Yin, Bertie Vidgen +1
cs.CLcs.CYarXiv:2303.04222v22023
Can Large Language Models Reason and Plan?
Subbarao Kambhampati
cs.AIcs.CLcs.LGarXiv:2403.04121v22024
Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries
Benjamin Heinzerling, Kentaro Inui
cs.CLarXiv:2008.09036v22020
Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses
Jaromir Savelka, Arav Agarwal, Marshall An +2
cs.CYcs.AIcs.CLarXiv:2306.10073v12023
Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements
Oliver G. B. Garrod, Robin A. A. Ince, Meng Liu +5
cs.CLcs.AIarXiv:2609.09425v12026
Sycophancy in Large Language Models: Causes and Mitigations
Lars Malmqvist
cs.CLcs.AIarXiv:2411.15287v12024
From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls
Hamed Jafarzadeh Asl, Yuanhao Yu, Vahid Partovi Nia
cs.LGcs.AIcs.CLarXiv:2609.09476v12026
Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?
Rishi Bommasani, Kathleen A. Creel, Ananya Kumar +2
cs.LGcs.AIcs.CLarXiv:2211.13972v12022
Guiding Large Language Models via Directional Stimulus Prompting
Zekun Li, Baolin Peng, Pengcheng He +3
cs.CLarXiv:2302.11520v42023
Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws
Zeyuan Allen-Zhu, Yuanzhi Li
cs.CLcs.AIcs.LGarXiv:2404.05405v12024
Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate
Kai Xiong, Xiao Ding, Yixin Cao +2
cs.CLcs.AIarXiv:2305.11595v32023
The Ghost in the Machine has an American accent: value conflict in GPT-3
Rebecca L Johnson, Giada Pistilli, Natalia Menédez-González +4
cs.CLcs.AIarXiv:2203.07785v12022
Augmenting Self-attention with Persistent Memory
Sainbayar Sukhbaatar, Edouard Grave, Guillaume Lample +2
cs.LGcs.CLstat.MLarXiv:1907.01470v12019
Auditable Emergency Triage for Maternal and Newborn Care in India
Shobhit Jagga, Aman Dalmia, Niharika Priyadarshini +7
cs.CLcs.AIcs.CYarXiv:2609.09356v12026
Self-Attentional Acoustic Models
Matthias Sperber, Jan Niehues, Graham Neubig +2
cs.CLarXiv:1803.09519v22018
Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?
Eric Lehman, Sarthak Jain, Karl Pichotta +2
cs.CLcs.AIcs.LGarXiv:2104.07762v22021
Eight Things to Know about Large Language Models
Samuel R. Bowman
cs.CLcs.AIarXiv:2304.00612v12023
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
Yiyang Ma, Xingchao Liu, Xiaokang Chen +11
cs.CVcs.AIcs.CLarXiv:2411.07975v22024
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
Xiangming Gu, Xiaosen Zheng, Tianyu Pang +5
cs.CLcs.CRcs.CVarXiv:2402.08567v22024

Computation and Language

GANDR: Claim Auditing for Verifiable Legal Answer Generation

DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs

LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation

GenSim: Generating Robotic Simulation Tasks via Large Language Models

Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning

Weak Supervision for Fake News Detection via Reinforcement Learning

Evaluating the Factual Consistency of Large Language Models Through News Summarization

Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning

Affective Neural Response Generation

End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning

Toward Gender-Inclusive Coreference Resolution

NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environments

Does Gender Matter? Towards Fairness in Dialogue Systems

Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture

Improving Cross-Lingual Token Representations by Adding a Pinch of SALT

OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples

Strangers to Themselves: What Language Models Say About Themselves Is Generic

DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction

From Audio to Semantics: Approaches to end-to-end spoken language understanding

Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?

deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets

How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial Scenarios

Advancing Multimodal Medical Capabilities of Gemini

Probing the Need for Visual Context in Multimodal Machine Translation

Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification

Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs

VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding

Intra-Prompt Parallel Decoding for Common-Context Question Answering

Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling

A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis

To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection

Fastformer: Additive Attention Can Be All You Need

OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text

When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination

SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness

Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA

Towards Improving Adversarial Training of NLP Models

ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

SemEval-2023 Task 10: Explainable Detection of Online Sexism

Can Large Language Models Reason and Plan?

Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries

Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses

Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements

Sycophancy in Large Language Models: Causes and Mitigations

From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

Guiding Large Language Models via Directional Stimulus Prompting

Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws

Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate

The Ghost in the Machine has an American accent: value conflict in GPT-3

Augmenting Self-attention with Persistent Memory

Auditable Emergency Triage for Maternal and Newborn Care in India

Self-Attentional Acoustic Models

Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?

Eight Things to Know about Large Language Models

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast