| 1 |
Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
Rohith Uppala
|
|
cs.CR
|
0 |
2 months ago |
| 2 |
AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing
Thomas Stephan Juzek
|
|
cs.CL
|
0 |
2 months ago |
| 3 |
IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization
Zixuan Chen, Jiaxiang Chen, ... (+5 more)
|
|
cs.LG
|
0 |
2 months ago |
| 4 |
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
Hao Li, Jingkun An, ... (+9 more)
|
|
cs.AI
|
0 |
1 month ago |
| 5 |
MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
Partha Pratim Saha, Samarth Raina, ... (+5 more)
|
|
cs.CL
|
0 |
2 months ago |
| 6 |
MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models
David Setiawan, Temuulen Khishigsuren, ... (+4 more)
|
|
cs.CL
|
0 |
1 month ago |
| 7 |
Inside the LLM Word Factory
Benzi Busigin, Yuval Pinter
|
|
cs.CL
|
0 |
1 month ago |
| 8 |
Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning
Jonathan von Rad, Louis Arts, ... (+7 more)
|
|
cs.CL
|
0 |
1 month ago |
| 9 |
Consistency Training Along the Transformer Stack
Sukrati Gautam, Neil Shah, ... (+8 more)
|
|
cs.LG
|
0 |
1 month ago |
| 10 |
AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents
Yang Li, Jiaxiang Liu, ... (+2 more)
|
|
cs.CL
|
0 |
1 month ago |
| 11 |
Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM
SooHwan Eom, Jay Shim, ... (+5 more)
|
|
cs.CL
|
0 |
1 month ago |
| 12 |
Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing
Mehmet Utku Colak
|
|
cs.AI
|
0 |
1 month ago |
| 13 |
Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering
Jieyuan Liu, Jianyang Gu, ... (+3 more)
|
|
cs.CL
|
0 |
1 month ago |
| 14 |
Beyond Layer Importance in Layer-wise Sparsity: An Inter-Layer Perturbation-Absorption Perspective
Tao Jing, Ningxin Wu, ... (+4 more)
|
|
cs.CL
|
0 |
1 month ago |
| 15 |
PACUTE: Phonology-, Affix-, and Character-level Understanding of Tokens for Filipino
Jann Railey Montalan, David Demitri Africa, ... (+4 more)
|
|
cs.CL
|
0 |
1 month ago |
| 16 |
CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment
Jiayue Cao, Zhicong Lu, ... (+7 more)
|
|
cs.CL
|
0 |
1 month ago |
| 17 |
Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents
Tianyu Ding, Jianhong Xin, Juan Pablo De la Cruz Weinstein
|
|
cs.LG
|
0 |
1 month ago |
| 18 |
Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark
Pratham Singla, Shivank Garg, ... (+2 more)
|
|
cs.CL
|
0 |
1 month ago |
| 19 |
Scaling LLM Knowledge Boundaries via Distribution-Optimized Synthesis
Songze Li, Yarong Lan, ... (+17 more)
|
|
cs.CL
|
0 |
1 month ago |
| 20 |
First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers
Arjun Pillai, Christian Hoang, Anjelo Jann Laroza
|
|
cs.CL
|
0 |
1 month ago |
| 21 |
Curiosity as Linguistic Intervention: Using LLM Tutoring Dialogues to Influence Exploratory Learning Behavior
Gevindu Ganganath, Pasindu Bolonghege, ... (+3 more)
|
|
cs.CL
|
0 |
1 month ago |
| 22 |
CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents
Youngwon Choi, Hyeonyu Kim, ... (+3 more)
|
|
cs.HC
|
0 |
1 month ago |
| 23 |
Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings
Pranav Bhandari, Nicolas Fay, ... (+3 more)
|
|
cs.CL
|
0 |
1 month ago |
| 24 |
PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM Agents
Aaditya Pai
|
|
cs.CR
|
0 |
1 month ago |
| 25 |
Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search
Sidhaarth Murali, João Coelho, ... (+4 more)
|
|
cs.AI
|
0 |
1 month ago |
| 26 |
From Parasocial Scripts to Dyadic Persistence in Autonomous AI-Agent Communities
Mohammadsadegh Abolhasani, Hamid Reza Firoozfar, ... (+2 more)
|
|
cs.CL
|
0 |
1 month ago |
| 27 |
ThinkProbe: Beyond Accuracy -- Structural Profiling of Open-Ended LLM Reasoning Traces via Non-Generative Thought Graphs
Mohamed Amine Kerkouri, Simon D. Hernandez, ... (+4 more)
|
|
cs.CL
|
0 |
1 month ago |
| 28 |
Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection
Hamid Reza Firoozfar, Mohammadsadegh Abolhasani, ... (+2 more)
|
|
cs.CL
|
0 |
1 month ago |
| 29 |
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents
Peng Xu, Sijia Chen, ... (+2 more)
|
|
cs.LG
|
0 |
1 month ago |
| 30 |
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
Dang Quang Thien Tran, Quang V. Dang, ... (+8 more)
|
|
cs.CL
|
0 |
29 days ago |
| 31 |
SEFORA: Student Essays with Feedback Corpus and LLM Feedback Evaluation Framework
Shayan Peyghambari Oskoui, Norah Almousa, ... (+6 more)
|
|
cs.CL
|
0 |
1 month ago |
| 32 |
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
Weicheng Ma, John Guerrerio, Soroush Vosoughi
|
|
cs.CL
|
0 |
22 days ago |