MEMPROBE is a benchmark for direct recovery of hidden user states from LLM agent memory, showing task success and memory recovery as distinct capabilities with moderate recovery scores around 0.6.
LaMP: When large language models meet personalization
12 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
12
Pith papers citing it
7
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and compose across users with 33,000x smaller footprint than per-user adapters.
IPQA is a new benchmark that measures how well models identify core user intents from history in personalized question answering, finding that performance is poor and declines with greater question complexity.
User memory in LLMs factors into three orthogonal axes where parametric adapters and retrieval show opposite strengths, with causal evidence from attention interventions and an alignment tax on RLHF models.
Highlighting is largely social (crowd predicts salience better than personal history), but individuality appears strongly in which salient passages a person selects, driven by thematic preferences.
Introduces Personal VCL formalization and benchmark revealing LMM context gaps, plus an Agentic Context Bank baseline that boosts personalized visual reasoning.
A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.
MemSlides introduces a three-part memory hierarchy (user profile, working, tool) with scoped local revision for multi-turn personalized slide generation.
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
PPRO improves user-aware memory retrieval in conversational agents by using derived user profiles for ranking and training a query rewriter via Group Relative Policy Optimization, with reported gains on LoCoMo and LongMemEval-S benchmarks.
Co-design workshops reveal both universal needs and personality-specific preferences for AI writing companions in functionality, interaction style, and visual form.
citing papers explorer
-
MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery
MEMPROBE is a benchmark for direct recovery of hidden user states from LLM agent memory, showing task success and memory recovery as distinct capabilities with moderate recovery scores around 0.6.
-
User as Engram: Internalizing Per-User Memory as Local Parametric Edits
User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and compose across users with 33,000x smaller footprint than per-user adapters.
-
IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering
IPQA is a new benchmark that measures how well models identify core user intents from history in personalized question answering, finding that performance is poor and declines with greater question complexity.
-
Substrate Asymmetry in User-Side Memory: A Diagnostic Framework
User memory in LLMs factors into three orthogonal axes where parametric adapters and retrieval show opposite strengths, with causal evidence from attention interventions and an alignment tax on RLHF models.
-
Personal Salience: Highlighting Is Social, but Individuality Lives in Selection
Highlighting is largely social (crowd predicts salience better than personal history), but individuality appears strongly in which salient passages a person selects, driven by thematic preferences.
-
Personal Visual Context Learning in Large Multimodal Models
Introduces Personal VCL formalization and benchmark revealing LMM context gaps, plus an Agentic Context Bank baseline that boosts personalized visual reasoning.
-
Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies
A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.
-
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision
MemSlides introduces a three-part memory hierarchy (user profile, working, tool) with scoped local revision for multi-turn personalized slide generation.
-
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
-
Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory
PPRO improves user-aware memory retrieval in conversational agents by using derived user profiles for ranking and training a query rewriter via Group Relative Policy Optimization, with reported gains on LoCoMo and LongMemEval-S benchmarks.
-
What Makes an AI Writing Companion a Good Fit? A Personality-Informed Co-Design Study
Co-design workshops reveal both universal needs and personality-specific preferences for AI writing companions in functionality, interaction style, and visual form.
- Alignment has a Fantasia Problem