Applied & Human-Centered · Computer Science & AI
Information Retrieval
The newest papers in Information Retrieval that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
979 papers, from 4 September 2026 to 5 November 2026: 979 arXiv preprints.
Get the few papers worth your time in Information Retrieval every morning.
Follow Information Retrieval and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 33
Towards Semi-Automatically Comparing Keyword-Based and Semantic Search Accuracy
The increasing importance of Information Retrieval (IR) in managing large datasets has highlighted significant limitations in traditional keyword-based search systems.Generated Query Expansion Still Helps Strong Sparse Retrieval: A Controlled Study with SPLADE-v3
Scientific queries are often brief, while relevant papers use specialized vocabulary.BITEM at the NTCIR-19 R2C2 Task: Predicting Confidence from Agentic RAG Pipeline Signals
The BITEM team entered both subtasks of the NTCIR-19 R2C2 task with a single agentic pipeline, in which a model searches, reads and records evidence over a movie corpus while an orchestrator holds…Auditable Long-Term Memory: A Deterministic Retrieval Chain Measured at 479/475 of 500 on LongMemEval-S
We evaluate an auditable long-term memory system on LongMemEval-S.Effective Dense Retrieval using Only In-Context Examples
Turning decoder-only large language models (LLMs) into strong dense retrievers typically requires some form of retriever training.Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
Answering questions about long videos often requires connecting events involving the same objects across hours or days.Privacy in Personalized AI Is a System Property, Not Just a Model Property
In personalized AI applications, such as conversational assistants and recommender systems, users interact not with models in isolation but with broader systems that access, infer, and reuse user…TAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories
Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they often vary in representation, indexing…Doc2LoRA Provides Decodable Representations of Scientific Ideas
Representing scientific papers as points in a space lets us search for similar papers and inquire about how fields relate to one another and drive innovation.AdaM-Rec: Adaptive Modality Routing for Multimodal Recommendation
While recent multimodal recommender systems have demonstrated the effectiveness of incorporating visual and textual information to improve downstream performance, most existing methods rely on…Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
Retrieval-Augmented Generation (RAG) is now the standard way to ground Large Language Models (LLMs) in external knowledge, yet the design space of retrieval pipelines is large and the trade-offs…Component-Aware Feedback for Self-Evolving Programs
LLM-guided evolutionary search can discover complex programs, but existing methods mostly only save candidate programs and fitness scores while discarding which component edits produced which…Exploring Forum Post Retrieval with Generative Modeling
Generative recommendation (GR) has emerged as an alternative to embedding-based retrieval, building on the success of generative models in language and vision.STITCH-RAG: Spatio-Temporal Influence Tracing over Topic Hypergraphs for Multi-Hop Retrieval-Augmented Generation
Multi-hop retrieval-augmented generation requires a retriever to connect evidence distributed across documents while preserving a concise, faithful generation context.RidgeRank: Efficient Visual Document Reranking via Score Fusion and a Shallow Linear Readout
Multimodal language models rerank visual document retrieval results accurately, but scoring every candidate page at full cost makes them slow.When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model
Does conversational memory need LLM-extracted facts, or is selecting the right raw turns enough?Measuring and Mitigating Identity-Cue Preference Drift in LLM-based Recommender Systems
In large language model-based recommender systems, identity cues embedded in prompts can steer recommendations toward group-level patterns even when the underlying behavioral evidence remains…SPRINT: Single-Step Generative Recommendation via Average Probability Velocity
Semantic ID (SID) based generative recommendation represents each item as a sequence of discrete tokens, and recommends by generating the SID of the item a user would like to interact with.When Harness Beats Scale, and When Reading Beats Both
We describe our system for DocSem, the document-grounded quantitative reasoning shared task at DocInsights 2026, and analyze why it succeeded on labeled data and failed on the test set.Correcting to Predict: Pseudo-Value Correction for Multimodal Attribute Value Extraction
Product attribute value extraction (AVE) is a fundamental task in e-commerce, aiming to identify specific values of predefined attributes from multimodal product profiles such as text and images.