Retrieval-augmented generation

Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.

3,480 stories · RSS feed

arXiv Machine Learning

Jun 2

Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment

arXiv:2606. 01456v1 Announce Type: new Abstract: Large language models are increasingly deployed as advisors whose objective is not aligned with the user's: recommenders optimize for engagement, sales assistants for purchases, negotiation agents for concessions.

By Hamidreza Hasani Balyani, Seyed Pouyan Mousavi Davoudi, Alireza Amiri-Margavi, Amin Gholami Davodi, Arshia Gharagozlou

llms rag agents benchmarks safety

arXiv Machine Learning

Jun 2

G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs

arXiv:2606. 01873v1 Announce Type: new Abstract: LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning.

By Yuhan Wang, Yibo Ding, Yutong Ye, Mufan Zhao, Wenbo Zhang, Ruijie Wang, Jianxin Li

llms rag fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 2

Differentially Private Datastore Generation for Retrieval-Augmented Inference

arXiv:2606. 01413v1 Announce Type: cross Abstract: It is crucial for modern on-device AI systems that rely on retrieval-augmented inference to release and share datastores without compromising individual privacy.

By Abdelrahman Abouelenein, Marwan Torki

rag benchmarks safety

arXiv Machine Learning

Jun 2

Chaining 2-FWL GNNs for Combinatorial Graph Alignment

arXiv:2510. 03086v2 Announce Type: replace Abstract: For the combinatorial graph alignment problem (GAP) -- finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs -- properly initialized FAQ remains a strong classical baseline, while existing GNN approaches struggle in the purely structural setting.

By Marc Lelarge

rag benchmarks safety

arXiv Machine Learning

Jun 2

Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach

arXiv:2509. 24627v2 Announce Type: replace Abstract: Embedding physical intuition into network architectures allows the learning of dynamics that enforce fundamental properties, such as energy conservation laws, thereby leading to physically-plausible predictions.

By Katharina Friedl, No\'emie Jaquier, Alyx Liao, Danica Kragic

rag

arXiv Machine Learning

Jun 2

Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs

arXiv:2602. 11641v2 Announce Type: replace Abstract: Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enabling GNNs to jointly model semantic and structural information.

By Yinlin Zhu, Di Wu, Xu Wang, Guocong Quan, Miao Hu

llms rag benchmarks safety

arXiv Machine Learning

Jun 2

PathCRF: Ball-Free Soccer Event Detection via Possession Path Inference from Player Trajectories

arXiv:2602. 12080v2 Announce Type: replace Abstract: Despite recent advances in AI, event data collection in soccer still relies heavily on labor-intensive manual annotation.

By Hyunsung Kim, Kunhee Lee, Sangwoo Seo, Sang-Ki Ko, Jinsung Yoon, Chanyoung Park

rag

arXiv Machine Learning

Jun 2

Test-Time Compute for Frozen Embedding Models through Agentic Program Search

arXiv:2605. 11374v5 Announce Type: replace Abstract: Test-time compute is widely believed to benefit only large reasoning models, leaving small models with nothing to gain.

By Han Xiao

llms rag agents

arXiv Machine Learning

Jun 2

Robust Frequency-Calibrated Virtual EEG Channel Generation from Four Frontal Electrodes for Wearable EEG Augmentation

arXiv:2605. 29263v2 Announce Type: replace Abstract: Low-channel wearable electroencephalography (EEG) is attractive for long-term monitoring, but four frontal electrodes provide only a sparse and spatially biased view of distributed scalp activity.

By Minghao Xiao

rag

arXiv Machine Learning

Jun 2

Domain Adaptation with a Single Vision-Language Embedding

arXiv:2410. 21361v2 Announce Type: replace-cross Abstract: Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in real-world autonomous driving scenarios, especially under rare or adverse conditions.

By Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick P\'erez, Raoul de Charette

rag agents computer-vision robotics fine-tuning multimodal

arXiv AI

Jun 2

MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models

arXiv:2606. 00909v1 Announce Type: cross Abstract: This work presents MLLM-Microscope, a novel system designed for analyzing the hidden representations within Multimodal Large Language Models (MLLMs).

By Ravil Mussabayev, Rustam Mussabayev

llms rag multimodal benchmarks

arXiv AI

Jun 2

Improving Visual Representation Alignment Generation with GRPO

arXiv:2606. 00583v1 Announce Type: cross Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between generative and discriminative representations.

By Shentong Mo, Sukmin Yun

llms rag diffusion safety

arXiv AI

Jun 2

LLMs Need Encoders for Semantic IDs Too

arXiv:2606. 00324v1 Announce Type: cross Abstract: Multimodal LLMs use dedicated encoders to bridge non-language modalities (vision encoders for images, depth models for audio codec tokens) because raw token embeddings alone cannot capture modality-specific structure.

By Xiangyi Chen, Zelun Wang, Xinyi Li, Yi-Ping Hsu, Jaewon Yang, Jiajing Xu

llms rag multimodal

arXiv AI

Jun 2

Test-Time Training for Zero-Resource Dense Retrieval Reranking

arXiv:2606. 01070v1 Announce Type: cross Abstract: Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings.

By Shiyan Liu, Yichen Li

rag benchmarks

arXiv Machine Learning

Jun 2

Beyond Sinusoids: A Morlet Wavelet Framework for Transformer Positional Encoding

arXiv:2606. 01258v1 Announce Type: new Abstract: Standard positional encodings for transformers - sinusoidal and rotary (RoPE) - treat every position as equally local: they encode where a token is, but not how far its positional influence should extend.

By Athanasios Zeris

llms rag

arXiv AI

Jun 2

Physics-Informed Neural Networks for Radial Consolidation of Combined Electroosmotic, Vacuum and Surcharge Preloading Considering Smear Effects

arXiv:2606. 00056v1 Announce Type: cross Abstract: This study develops a dimensionless multi-domain physics-informed neural network (PINN) framework for electro-osmotic radial consolidation considering smear effects and combined vacuum and surcharge loading.

By Dong Li, Yapeng Cao, Shuai Huang, Yujun Cui, Haiping Fu, Lu Yang, He Wei

rag

arXiv AI

Jun 2

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

arXiv:2606. 02373v1 Announce Type: new Abstract: Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which constraints remain open, and which claims have actually been checked.

By Pengcheng Jiang, Zhiyi Shi, Kelly Hong, Xueqiang Xu, Jiashuo Sun, Jimeng Sun, Hammad Bashir, Jiawei Han

rag agents reinforcement-learning benchmarks

arXiv AI

Jun 2

Tracking the Behavioral Trajectories of Adapting Agents

arXiv:2606. 02536v1 Announce Type: new Abstract: Text files such as skill files, memory files, and behavioral configuration files play a central role in defining how modern agents act.

By Jonah Leshin, Manish Shah, Ian Timmis

rag agents

arXiv AI

Jun 2

TrafficRAG: A Multimodal RAG Framework for Traffic Accident Liability Determination

arXiv:2606. 01737v1 Announce Type: new Abstract: Traffic accident liability analysis is a critical yet challenging task in intelligent transportation and legal assistance.

By Xu Li, Zedong Fu, Xinyi Li, Xun Han

llms rag multimodal

arXiv AI

Jun 2

RL-ACRGNet: Reinforcement Learning-Based Chest Radiology Report Generation Network

arXiv:2606. 02035v1 Announce Type: new Abstract: Medical imaging interpretation is a foundational pillar of modern clinical diagnostics, yet the manual generation of radiology reports remains a time-consuming process prone to interpretation inconsistencies.

By Yogesh Kumar Meena, Saurabh Agarwal, K. V. Arya

rag reinforcement-learning benchmarks

Get the daily briefing