Get Started
Topic · 3 recaps
Information Retrieval
Search, ranking, recommendation, and retrieval systems — including the dense-retrieval methods that power modern RAG pipelines.
Play all
...
Posts
Questions
Home
Topics
Search
Library
Questions researchers are working on
Follow a question through Rcap’s explanations and the latest papers addressing it.
Search
How can a model select the correct entity-specific parametric memory for graph queries without query-time text or semantic similarity?
Graph facts stored in separate parameter memories avoid repeating retrieved subgraphs in each prompt. However, a query’s answer may reside in one specific entity’s memory even when another entity is semantically similar, making ordinary similarity retrieval unreliable.
How can a single search agent improve multi-hop web research without sub-agents or test-time verification?
Multi-hop web research requires an agent to connect evidence across several pages while retaining the information needed for later steps. Long search trajectories can overwhelm the available context, making both training and reliable performance difficult without additional agents or verification passes.
How can advertising enter token-by-token generated responses while preserving incentive compatibility and response quality?
Generated responses do not offer the fixed advertising slots assumed by conventional mechanisms, so advertising may need to influence the generation process itself. That influence must not compromise truthful advertiser participation or the usefulness of the response.
How can agentic vision-language models acquire and use necessary external evidence without redundant tool calls?
Complex image-grounded questions may require visual details or external knowledge unavailable in the initial input. Models may pursue irrelevant evidence or fail to extract useful information from tool outputs, while final-answer supervision does not clearly teach effective evidence acquisition.
How can agents find people across cameras from vague witness clues under spatial-temporal and turn constraints?
Witness accounts may be partial or ambiguous, while relevant observations are distributed across camera locations and time. An agent must choose questions and searches before its interaction budget runs out.
How can AI-agent memory survive model upgrades without losing retrieval or repairability?
A new model may interpret old notes differently or query existing embeddings differently, even when the memory store is unchanged. Summarization can discard evidence, while embedding changes can make stored information harder to retrieve or repair.
How can assistants identify when a request conflicts with implicit user-specific circumstances?
A seemingly reasonable request may become inappropriate because of facts about the user that the request does not mention. The assistant must connect those user-specific facts to the request before determining whether a conflict exists.
How can audio-captioning datasets represent fine-grained acoustic detail and perceptual ambiguity for better audio retrieval?
Many audio-captioning datasets provide generic descriptions and only one caption per clip, even though listeners may describe the same sounds in different valid ways. Missing acoustic detail and semantic variation can limit models trained for audio retrieval and related audio-language tasks.
How can biomedical question answering retrieve the right evidence and produce accurate answers?
Biomedical QA must identify useful evidence from document collections and turn it into answers that remain accurate and grounded. Retrieval quality and answer quality are related but distinct parts of the problem.
How can candidate generation recover corporate-family links between supplier records with no shared name evidence?
Suppliers in the same corporate family may be deliberately represented as different entities, while the relationship may appear in neither record. When their names share no distinctive evidence, blocking can exclude the true pair before matching is applied.
How can coding agents maintain accurate repository context as codebases evolve without repeated discovery?
Coding agents repeatedly search, navigate, and retain repository information, while code edits can invalidate indexes and prior context. Disconnected tools and task-local histories make it costly to keep retrieved locations and context aligned with the current commit.
How can coding agents reliably implement systems-level requirements and detect the defects they introduce?
Systems-level tasks combine interacting requirements such as schema design, asynchronous orchestration, configuration, and retrieval behavior. Defects can violate these constraints while remaining undetected, and claimed fixes may go unverified without regression measurement.
How can compact text embedding models improve retrieval and generalization through better training and data quality?
Compact embedding models can underperform on retrieval and generalization when development emphasizes data scaling or synthesis without sufficiently addressing training methods and data quality. The problem is to improve their representations without relying on substantially larger models.
How can composed image retrieval distinguish changed, preserved, and removed visual details?
A whole-image similarity score can mix the edit with details that should remain or disappear. Retrieval therefore needs to represent different roles of the reference and text without losing fine-grained evidence.
How can conformal prediction preserve coverage while removing irrelevant content from NLP document extracts?
Document selection for language tasks must retain enough pertinent information for the task while excluding irrelevant material. Designing relevance scores that make this tradeoff reliably across tasks is difficult without hand-crafted prompts for each one.
How can conversational agents retrieve the right memories when users rely on implicit conversational context?
Conversational users may refer to earlier information indirectly without stating which fact they need. Systems that perform well on explicit fact questions can therefore miss memories needed to ground an appropriate response.
How can cross-modal generative retrieval avoid hallucinating visual details missing from concise text queries?
Concise text queries often omit fine-grained visual details that autoregressive decoders must nevertheless predict. Forced predictions during constrained identifier decoding can cause irrelevant visual candidates to outrank relevant ones.
How can data-centric agents reuse prior intent-to-object discoveries without causing retrieval interference?
Data-centric agents often discard mappings between task intent and relevant data objects after discovery, forcing similar searches to start over. Reusing those mappings may improve retrieval, but stale or conflicting memories can interfere with later discovery.
How can dense retrievers specialize for biomedical search without sacrificing general-domain retrieval?
Training retrievers across biomedical and general domains can be costly, and mixed-domain training may blur capabilities that are useful in specialized settings. The central difficulty is improving biomedical retrieval while preserving broad-domain performance.
How can document retrieval find the correct record when large collections share nearly identical visual templates?
Enterprise repositories may contain many records with nearly identical layouts but different contents. This visual similarity can make embeddings insufficiently discriminative, causing retrieval to select the wrong document.
Previous
1 / 6
Next