TILens turns technical updates into a focused daily brief: official releases,
trusted reporting, and practitioner analysis, deduplicated and organized by topic.
Hey Devs! 👋 I wanted to share a quick breakdown of a project I’ve been building called Prankwish.com — a platform that connects users with authentic, real-world performers to deliver personalized birthday, surprise, and…
arXiv:2609.08330v1 Announce Type: new Abstract: Table detection is a core task in document analysis, supporting downstream applications such as information retrieval, document reconstruction, and visual question…
arXiv:2609.09854v1 Announce Type: cross Abstract: Low-bit quantization can achieve high recall on some vector representations and fail sharply on others, while average distortion and global rank correlation do not…
arXiv:2609.10237v1 Announce Type: cross Abstract: A graph retrieval-augmented generation pipeline chooses which triples to put in the prompt, a syntax to write them in, an order to write them in, and a sentence telling…
arXiv:2609.09556v1 Announce Type: cross Abstract: Neural networks can leverage feature superposition to encode more concepts than dimensions, but cross-feature interference constrains the linear accessibility of…
arXiv:2609.10293v1 Announce Type: cross Abstract: In high-stakes domains such as legal practice, a language-model answer is only useful to the extent that a reader can verify each claim against the source the system…
arXiv:2609.09381v1 Announce Type: new Abstract: Livestock population data disaggregated by age, sex, and production are important inputs to calculations and models that inform our understanding of global health, yet…
arXiv:2609.10046v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as interfaces for information retrieval, but they remain prone to hallucinations and faithfulness errors, in which the…
arXiv:2604.10641v2 Announce Type: replace-cross Abstract: Synthetic face generators can produce many nominal identities, but nominal count does not determine how many are jointly distinguishable under a specified…
arXiv:2608.11889v2 Announce Type: replace-cross Abstract: Prompting-based (i.e., non-fine-tuning) Text-to-SQL methods, where underlying large language model parameters are not changed for the task, face three problems:…
arXiv:2609.10155v1 Announce Type: cross Abstract: We approach a cognitive simulation perspective on episodic and semantic memory in multiple-choice question answering by incorporating text from individual text corpora…
arXiv:2502.01555v3 Announce Type: replace Abstract: Associating user search queries with the correct brand entity is critical for e-commerce product retrieval, yet remains challenging due to the brevity of queries…
arXiv:2609.10239v1 Announce Type: new Abstract: Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversized contexts that…
arXiv:2609.10430v1 Announce Type: cross Abstract: Enterprise data lakes accumulate tables faster than human stewards can document or classify them, leaving columns with missing descriptions and unassigned governance…
arXiv:2609.09703v1 Announce Type: new Abstract: Large language models are increasingly used as relevance judges, yet their labels can shift with prompt surface form. We study one such feature -- tone -- on 3,498 TREC…
arXiv:2609.09878v1 Announce Type: new Abstract: How often does a generative assistant persuade someone to buy, or persuade them not to buy? Conversation logs contain recommendations, but they do not necessarily record…
arXiv:2609.09496v1 Announce Type: new Abstract: Algorithmic outputs now populate the digital environments through which contemporary life is organized. The role of law in facilitating and constituting (rather than…
arXiv:2609.05637v2 Announce Type: replace-cross Abstract: A popular way to improve Retrieval-Augmented Generation (RAG) is to rewrite the user's question into several variants and search with all of them. We test…
arXiv:2609.07629v1 Announce Type: cross Abstract: Democratizing access to the knowledge held in large corpora of tables such as data lakes is emerging as a central research challenge. Research in this space is advancing…