数据来源：ArXiv Domain LLM Domain Papers1. PsyBer-Agent: A Psychology-Driven User Agent for Recommender SystemsAbstract:Evaluating recommender systems before deployment requires simulators that remain realistic over long, closed-loop interaction cycles. Current LLM-based agents generally function as surface imitators that generate realistic short-term responses but fail to capture the underlying user dynamics such as fatigue, affect, and shifting preferences. We propose PsyBer-Agent, a psychology-i ...

数据来源：ArXiv Domain LLM Domain Papers1. Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt CollectionAbstract:Voice agents built on large language models (LLMs) now handle customer calls, but in regulated applications completing the task is not enough: the agent must follow a conversational flow set by law. In debt collection, it must confirm it is speaking to the debtor before mentioning the debt, identify itself and the creditor, state ...

数据来源：ArXiv Domain LLM Domain Papers1. DeepUnfolding_Agent: A Classical_Quantum Adaptive Control APIAbstract:Adaptive optimization workflows in machine learning, federated learning, quantum machine learning, and hybrid classical quantum systems often embed controller logic directly inside task specific training scripts. This coupling limits reuse, reproducibility, safety validation, and fair comparison across execution environments. This paper presents DeepUnfolding Agent, a schema-driven FastA ...

数据来源：ArXiv Domain LLM Domain Papers1. DeepUnfolding_Agent: A Classical_Quantum Adaptive Control APIAbstract:Adaptive optimization workflows in machine learning, federated learning, quantum machine learning, and hybrid classical quantum systems often embed controller logic directly inside task specific training scripts. This coupling limits reuse, reproducibility, safety validation, and fair comparison across execution environments. This paper presents DeepUnfolding Agent, a schema-driven FastA ...

数据来源：ArXiv Domain LLM Domain Papers1. DeepUnfolding_Agent: A Classical_Quantum Adaptive Control APIAbstract:Adaptive optimization workflows in machine learning, federated learning, quantum machine learning, and hybrid classical quantum systems often embed controller logic directly inside task specific training scripts. This coupling limits reuse, reproducibility, safety validation, and fair comparison across execution environments. This paper presents DeepUnfolding Agent, a schema-driven FastA ...

数据来源：ArXiv Domain LLM Domain Papers1. Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language ModelsAbstract:In a small language model the vocabulary is the single largest part. In Gemma 3 270M the embedding table holds 168M of 268M parameters, and because quantisation methods leave the embedding in 16-bit, it is also most of the file once the rest of the model is compressed. We ask what that table actually buys. We replace it with one frozen table of 512-bit codes, ...

数据来源：ArXiv Domain LLM Domain Papers1. Modeling Human Behavior in the Prisoner’s Dilemma with Large Language ModelsAbstract:The Prisoner’s Dilemma has long served as a foundational framework for studying human decision-making and cooperative outcomes across social scenarios, yet human behavior consistently deviates from predictions of fully rational economic theory. Previous works have studied human and LLM outcomes in the Prisoner’s Dilemma; however, these studies have lacked at least one key ...

数据来源：ArXiv Domain LLM Domain Papers1. H2DF: Calibrated Target Bands for Controllable Language-Model UnlearningAbstract:Gradient ascent (GA) is a simple language-model unlearning baseline, but it continues increasing forget loss after useful forgetting has occurred. This unbounded pressure can damage retained utility and make forgotten examples abnormally high-loss. We introduce H2DF, a calibrated target-band objective that applies GA-like pressure below a data-dependent lower target and suppre ...

数据来源：ArXiv Domain LLM Domain Papers1. How Far Can the Gemma 4 Speech Encoder Go Without Changing Its Weights? Saudi and Gulf Arabic Speech Recognition with a Frozen and an Adapter-Augmented EncoderAbstract:We study the 305M-parameter audio encoder shared by Gemma 4 and EmbeddingGemma 2 (bit-identical to that of Gemma 4 E2B except for the final audio-embedding projection) for Saudi and Gulf Arabic speech recognition, without changing any of its pretrained weights; the adapters of our adapted sy ...

数据来源：ArXiv Domain LLM Domain Papers1. baseVultra: Compact Nonlinear Recurrence with Reallocated CapacityAbstract:Nonlinear recurrent networks remain useful for streaming sequence modeling, yet gated cell design is still dominated by LSTM and GRU. We study whether recurrent computation can be reallocated away from gate transforms and toward candidate generation. We propose baseVultra, a compact recurrent cell that concentrates the dense recurrent budget on a single H x H candidate-generation ma ...

数据来源：ArXiv Domain LLM Domain Papers1. baseVultra: Compact Nonlinear Recurrence with Reallocated CapacityAbstract:Nonlinear recurrent networks remain useful for streaming sequence modeling, yet gated cell design is still dominated by LSTM and GRU. We study whether recurrent computation can be reallocated away from gate transforms and toward candidate generation. We propose baseVultra, a compact recurrent cell that concentrates the dense recurrent budget on a single H x H candidate-generation ma ...

数据来源：ArXiv Domain LLM Domain Papers1. Validating the Comparison, Not Just the Scorer: Why Overall Accuracy Can Mislead in Interactive LLM EvaluationAbstract:Many LLM studies compare how models respond to different follow-up prompts. For example, one prompt may neutrally ask a model to reconsider, while another insists that an invented film really exists. The difference is used to measure the effect of conversational pressure. An automatic scorer then labels whether each response makes an unsup ...

数据来源：ArXiv Domain LLM Domain Papers1. ReCoPII: A Relation-Grounded Framework for Building Contextual PII Masking DatasetsAbstract:Training contextual masking systems for personally identifiable information (PII) requires examples distinguishing maskable from preservable mentions of one entity type, but privacy restrictions limit access to real data. Author-based augmentation (SPY) labels mentions unrelated to the author as non-PII, presuming a single data subject and overlooking others. We pro ...

数据来源：ArXiv Domain LLM Domain Papers1. ReCoPII: A Relation-Grounded Framework for Building Contextual PII Masking DatasetsAbstract:Training contextual masking systems for personally identifiable information (PII) requires examples distinguishing maskable from preservable mentions of one entity type, but privacy restrictions limit access to real data. Author-based augmentation (SPY) labels mentions unrelated to the author as non-PII, presuming a single data subject and overlooking others. We pro ...

数据来源：ArXiv Domain LLM Domain Papers1. ReCoPII: A Relation-Grounded Framework for Building Contextual PII Masking DatasetsAbstract:Training contextual masking systems for personally identifiable information (PII) requires examples distinguishing maskable from preservable mentions of one entity type, but privacy restrictions limit access to real data. Author-based augmentation (SPY) labels mentions unrelated to the author as non-PII, presuming a single data subject and overlooking others. We pro ...