Natural Language Processing

Natural language processing covers how machines represent, understand, and generate human language. Articles here move from foundational ideas like embeddings and attention to current research on language models, retrieval, and evaluation, written to connect the theory with the systems people use today.

RideJudge: How an 8B Model Outperforms 32B Baselines at Ride-Hailing Dispute Resolution

RideJudge: How an 8B Model Outperforms 32B Baselines at Ride-Hailing Dispute Resolution

Leave a Comment / Machine Learning, Multimodal AI, Natural Language Processing /

RideJudge: How an 8B Model Outperforms 32B Baselines at Ride-Hailing Dispute Resolution | AI Trend Blend AITrendBlend Machine Learning Computer Vision About LLM Reasoning · Applied AI · arXiv:2603.17328 · Nanjing University & Didi Chuxing (2026) · 19 min read RideJudge: Teaching an 8B Model to Out-Think 32B Rivals on the Hardest Calls in Ride-Hailing […]

RideJudge: How an 8B Model Outperforms 32B Baselines at Ride-Hailing Dispute Resolution Read More »

Goal-Oriented Graphs: How NTU Researchers Finally Taught LLMs to Plan Like Humans in Minecraft.

Goal-Oriented Graphs: How NTU Researchers Finally Taught LLMs to Plan Like Humans in Minecraft

Leave a Comment / Machine Learning, Agent Systems, Natural Language Processing /

Goal-Oriented Graphs: How NTU Researchers Finally Taught LLMs to Plan Like Humans in Minecraft | AI Trend Blend LLM Agents & Reasoning Goal-Oriented Graphs: How NTU Researchers Finally Taught LLMs to Plan Like Humans GraphRAG shreds procedural knowledge into thousands of disconnected fragments. A new framework from Nanyang Technological University puts it back together —

Goal-Oriented Graphs: How NTU Researchers Finally Taught LLMs to Plan Like Humans in Minecraft Read More »

GATES: How Consensus Gating Fixed the Broken Promise of Self-Distillation in Language Models.

GATES: How Consensus Gating Fixed the Broken Promise of Self-Distillation in Language Models

Leave a Comment / Machine Learning, Natural Language Processing /

GATES: How Consensus Gating Fixed the Broken Promise of Self-Distillation in Language Models | AI Trend Blend Self-Supervised Learning · arXiv:2602.20574v1 [cs.LG] · University of Maryland, College Park · 18 min read GATES: How Consensus Gating Fixed the Broken Promise of Self-Distillation in Language Models Researchers at the University of Maryland trained a model to

GATES: How Consensus Gating Fixed the Broken Promise of Self-Distillation in Language Models Read More »

Overview of DSKD training.

DSKD: How Sense Dictionaries Are Finally Making Decoder LLMs Smarter Without Slowing Them Down

Leave a Comment / Machine Learning, Natural Language Processing /

DSKD: How Sense Dictionaries Are Finally Making Decoder LLMs Smarter Without Slowing Them Down | AI Research AITrendBlend Machine Learning About Natural Language Processing · arXiv:2602.22351v1 [cs.CL] · 15 min read DSKD: The Lexical Knowledge Injection That Finally Works for Decoder Language Models How researchers at RPI and IBM Research taught generative LLMs to understand

DSKD: How Sense Dictionaries Are Finally Making Decoder LLMs Smarter Without Slowing Them Down Read More »

ToDi, Per Token KL Divergence Control for LLM Distillation.

ToDi: Per Token KL Divergence Control for LLM Distillation

1 Comment / Machine Learning, Knowledge Distillation, Natural Language Processing /

Machine Learning › Knowledge Distillation › Paper Analysis Knowledge Distillation Forward KL Reverse KL LLM Compression Instruction Following Paper Analysis Analysis by the aitrendblend editorial team · October 2025 · 13 min read · arXiv:2505.16297 aitrendblend.com · Knowledge Distillation ToDi, Per Token Control of KL Divergence in LLM Distillation A seven billion parameter model writes

ToDi: Per Token KL Divergence Control for LLM Distillation Read More »