Assessing the Reliability and Validity of Large Language Models for Automated Assessment of Student Essays in Higher Education
arxiv.org·18h
🔍Retrieval-augmented generation
Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs
arxiv.org·18h
🔧Systems-level optimizations for LLM serving
TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
arxiv.org·18h
✨Model optimizations in LLMs
UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu
arxiv.org·18h
✨Model optimizations in LLMs
Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges
arxiv.org·1d
💬Prompt optimizations for LLM serving
ProCut: LLM Prompt Compression via Attribution Estimation
arxiv.org·18h
💬Prompt optimizations for LLM serving
A comprehensive taxonomy of hallucinations in Large Language Models
arxiv.org·18h
🔍Retrieval-augmented generation
Optimal Scheduling Algorithms for LLM Inference: Theory and Practice
arxiv.org·18h
🔧Systems-level optimizations for LLM serving
From Monolingual to Bilingual: Investigating Language Conditioning in Large Language Models for Psycholinguistic Tasks
arxiv.org·18h
🔍Retrieval-augmented generation
Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR
arxiv.org·18h
🔍Retrieval-augmented generation
Confidence-Diversity Calibration of AI Judgement Enables Reliable Qualitative Coding
arxiv.org·18h
✨Model optimizations in LLMs
Recognising, Anticipating, and Mitigating LLM Pollution of Online Behavioural Research
arxiv.org·18h
✨Model optimizations in LLMs
LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points
arxiv.org·18h
🔢Quantization of LLMs
CAMA: Enhancing Mathematical Reasoning in Large Language Models with Causal Knowledge
arxiv.org·18h
✨Model optimizations in LLMs
Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models
arxiv.org·18h
🔍Retrieval-augmented generation
Do LLMs produce texts with "human-like" lexical diversity?
arxiv.org·1d
🔍Retrieval-augmented generation
Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection
arxiv.org·1d
✨Model optimizations in LLMs
Co-Reward: Self-supervised Reinforcement Learning for Large Language Model Reasoning via Contrastive Agreement
arxiv.org·1d
✨Model optimizations in LLMs
From EMR Data to Clinical Insight: An LLM-Driven Framework for Automated Pre-Consultation Questionnaire Generation
arxiv.org·1d
🔍Retrieval-augmented generation
MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
arxiv.org·18h
🔢Quantization of LLMs