Reinforcement learning recruits rather than creates a functional welfare axis in language models, as reward and punishment vectors from a maze task generalize to unrelated settings and appear in pretrain-only models.
Steering llama 2 via contrastive activation addition
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
NLAC architecture translates natural language requests to access policies via LLMs, with embedding-based subgraph selection enabling up to 98.7% accuracy on large networks per NLACBench evaluations.
Adding a Bayesian source memory for market-feedback adaptive retrieval to a frozen LLM improves macro-F1 from 0.438 to 0.471 and portfolio Sharpe from 0.52 to 0.84 in point-in-time financial event-impact prediction.
A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.
AGPO adaptively sets trust-region size and exploration temperature from group reward dispersion, entropy, and KL drift, yielding higher scores than PPO and GRPO on nine math benchmarks under fixed token budget.
AgriIR is a configurable RAG framework using modular stages and 1B-parameter models to deliver grounded, citable answers for Indian agricultural information access.
A review of 114 studies classifies motivations into nine categories, analyzes common models and benchmarks, synthesizes challenges into six categories with 26 subcategories and solutions, and identifies six future research directions with 18 subcategories.
citing papers explorer
-
How's it going? Reinforcement learning in language models recruits a functional welfare axis
Reinforcement learning recruits rather than creates a functional welfare axis in language models, as reward and punishment vectors from a maze task generalize to unrelated settings and appear in pretrain-only models.
-
Natural Language Access Control (NLAC): From Help Desk Requests to Structured Policies
NLAC architecture translates natural language requests to access policies via LLMs, with embedding-based subgraph selection enabling up to 98.7% accuracy on large networks per NLACBench evaluations.
-
Point-in-Time Financial RAG with Frozen LLMs and Market-Feedback Adaptive Retrieval
Adding a Bayesian source memory for market-feedback adaptive retrieval to a frozen LLM improves macro-F1 from 0.438 to 0.471 and portfolio Sharpe from 0.52 to 0.84 in point-in-time financial event-impact prediction.
-
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs
A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.
-
AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback
AGPO adaptively sets trust-region size and exploration temperature from group reward dispersion, entropy, and KL drift, yielding higher scores than PPO and GRPO on nine math benchmarks under fixed token budget.
-
AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval
AgriIR is a configurable RAG framework using modular stages and 1B-parameter models to deliver grounded, citable answers for Indian agricultural information access.
-
LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review
A review of 114 studies classifies motivations into nine categories, analyzes common models and benchmarks, synthesizes challenges into six categories with 26 subcategories and solutions, and identifies six future research directions with 18 subcategories.