#Conversational AI

12개의 포스트

[논문리뷰] Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation

arXiv에 게시된 'Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation' 논문에 대한 자세한 리뷰입니다.

#Review #Financial Recommendation #Conversational AI #Large Language Models #Utility-Grounded Evaluation #Behavioral Finance #Stock Recommendation #Longitudinal Benchmark #Inverse Optimization

2026년 2월 24일

[논문리뷰] SARAH: Spatially Aware Real-time Agentic Humans

Alexander Richard이 arXiv에 게시한 'SARAH: Spatially Aware Real-time Agentic Humans' 논문에 대한 자세한 리뷰입니다.

#Review #Embodied Agents #Real-time #Conversational AI #Motion Generation #Spatially Aware #VR #Causal Models #Flow Matching #Gaze Control

2026년 2월 22일

[논문리뷰] Linear representations in language models can change dramatically over a conversation

arXiv에 게시된 'Linear representations in language models can change dramatically over a conversation' 논문에 대한 자세한 리뷰입니다.

#Review #Language Models #Representation Analysis #Interpretability #In-Context Learning #Representation Dynamics #Factuality #Conversational AI #Activation Steering

2026년 1월 28일

[논문리뷰] Reasoning Models Generate Societies of Thought

James Evans이 arXiv에 게시한 'Reasoning Models Generate Societies of Thought' 논문에 대한 자세한 리뷰입니다.

#Review #Reasoning Models #Large Language Models (LLMs)#Multi-Agent Systems #Society of Thought #Mechanistic Interpretability #Reinforcement Learning #Cognitive Diversity #Conversational AI

2026년 1월 18일

[논문리뷰] Toxicity Ahead: Forecasting Conversational Derailment on GitHub

Kostadin Damevski이 arXiv에 게시한 'Toxicity Ahead: Forecasting Conversational Derailment on GitHub' 논문에 대한 자세한 리뷰입니다.

#Review #Conversational AI #Toxicity Detection #LLM #Prompt Engineering #Open Source Software #GitHub #Derailment Forecasting

2025년 12월 23일

[논문리뷰] Adaptive Multi-Agent Response Refinement in Conversational Systems

arXiv에 게시된 'Adaptive Multi-Agent Response Refinement in Conversational Systems' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Multi-Agent Systems #Conversational AI #Response Refinement #Dynamic Agent Selection #Persona Alignment #Factual Grounding #Coherence

2025년 11월 11일

[논문리뷰] CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs

arXiv에 게시된 'CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Instruction Tuning #BabyLMs #Small-scale LMs #Curriculum Learning #Conversational AI #Question Answering #Zero-shot Evaluation #SuperGLUE

2025년 10월 31일

[논문리뷰] ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models

Sean O'Brien이 arXiv에 게시한 'ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-turn Conversation #Large Language Models (LLMs)#Context Management #Entropy-guided Resetting #Uncertainty Quantification #Performance Degradation #Prompt Engineering #Conversational AI

2025년 10월 20일

[논문리뷰] Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models

arXiv에 게시된 'Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reactive Transformer #Stateful LLM #Event-Driven AI #Asynchronous Memory #Conversational AI #Linear Scaling #Short-Term Memory (STM)#Memory Attention

2025년 10월 7일

[논문리뷰] Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap

Hengfan Zhang이 arXiv에 게시한 'Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap' 논문에 대한 자세한 리뷰입니다.

#Review #Voice AI #LLM #Reasoning #Benchmark #Modality Gap #Latency #Speech Recognition #Generative AI #Real-time Systems #Conversational AI

2025년 10월 1일

[논문리뷰] OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models

Alex Endert이 arXiv에 게시한 'OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models (LLMs)#Human-Computer Interaction (HCI)#Conversational AI #Goal Tracking #Visualization #Multi-Turn Dialogue #User Interface Design #Sensemaking

2025년 8월 29일

[논문리뷰] Investigating Hallucination in Conversations for Low Resource Languages

Fatemeh Jamshidi이 arXiv에 게시한 'Investigating Hallucination in Conversations for Low Resource Languages' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Hallucination #Low-resource Languages #Conversational AI #ROUGE Score #Cross-lingual Evaluation #Factual Consistency

2025년 8월 4일