Papers196

Legal RAG Bench: an end-to-end benchmark for legal RAG

Abdur-Rahman Butler, Umar ButlerMar 2arXiv

Legal RAG Bench is a new, end-to-end test that checks how well legal AI systems find information and use it to answer tough, real-world legal questions.

#legal RAG#retrieval-augmented generation#embedding models

PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval

Beginner

Tianyi Xu, Rong Shan et al.Mar 2arXiv

PhotoBench is a new test built from real people’s photo albums to see if AI can find photos based on what you truly mean, not just what you see.

#PhotoBench#personalized photo retrieval#multi-source reasoning

SciDER: Scientific Data-centric End-to-end Researcher

Beginner

Ke Lin, Yilin Lu et al.Mar 2arXiv

SciDER is a team of smart AI helpers that can run almost the whole research process: think of ideas, read raw data, write and run code, and improve itself with feedback.

#data-centric AI#AI research agent#self-evolving memory

Spectral Attention Steering for Prompt Highlighting

Beginner

Weixian Waylon Li, Yuchen Niu et al.Mar 1arXiv

This paper teaches a new way to make a language model pay extra attention to the exact words you highlight in a prompt.

#attention steering#prompt highlighting#key embeddings

CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

Beginner

Xinyu Zhu, Yihao Feng et al.Mar 1arXiv

CHIMERA is a small (about 9,000 examples) but very carefully built synthetic dataset that teaches AI to solve hard problems step by step.

#CHIMERA dataset#synthetic data generation#chain-of-thought

Memory Caching: RNNs with Growing Memory

Beginner

Ali Behrouz, Zeman Li et al.Feb 27arXiv

Recurrent neural networks (RNNs) are fast but forgetful because they squeeze everything they’ve seen into a tiny, fixed memory.

#Memory Caching#Recurrent Neural Networks#Attention

Humans and LLMs Diverge on Probabilistic Inferences

Beginner

Gaurav Kamath, Sreenath Madathil et al.Feb 26arXiv

Humans often make guesses about the world that are likely but not certain, and this paper studies how humans and AI compare at doing that.

#probabilistic reasoning#uncertainty calibration#natural language inference

Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos

Beginner

Ziqi Gao, Jieyu Zhang et al.Feb 26arXiv

This paper builds a giant, automatically made video library called SVG2 that tells who is in a video, what they look like, and how they interact over time.

#video scene graph#spatio-temporal reasoning#panoptic segmentation

CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era

Beginner

Zhengqing Yuan, Kaiwen Shi et al.Feb 26arXiv

The paper tackles a new integrity problem in science: large language models sometimes invent realistic-looking citations that do not exist.

#citation verification#hallucinated citations#scholarly integrity

Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning

Beginner

Chris Samarinas, Haw-Shiuan Chang et al.Feb 26arXiv

SLATE is a new way to teach AI to think step by step while using a search engine, giving feedback at each step instead of only at the end.

#retrieval-augmented reasoning#reinforcement learning#GRPO

MediX-R1: Open Ended Medical Reinforcement Learning

Beginner

Sahal Shaji Mullappilly, Mohammed Irfan Kurpath et al.Feb 26arXiv

MediX-R1 teaches medical AI models to give clear, free-form answers (not just A, B, C, or D) and to explain their thinking.

#medical multimodal RL#open-ended reinforcement learning#composite reward

Imagination Helps Visual Reasoning, But Not Yet in Latent Space

Beginner

You Li, Chi Chen et al.Feb 26arXiv

The paper asks a simple question: do the model’s invisible “imagination tokens” actually help it reason about images?

#multimodal large language model#visual reasoning#latent visual reasoning

1 2 3 4 5