I found a tool to reduce hallucinations in any LLM! TLM (trustworthy language model) is a simple, plug-and-play solution that curbs hallucinations, crucial because LLMs lose real-world value if you can’t trust their outputs. It was tested on OpenAI’s SimpleQA dataset (4,000+
LLMS
-
Essential AI Benchmarks and Evaluation Metrics for LLMs
By
–
Must Know Benchmarks and Evals: Knowledge: @hendrycks
' MMLU and MATH, @idavidrein
's GPQA and BIG-Bench and their polyunsaturated 2025 variants. Ditto Math lvl 5, AIME, @tamaybes
's FrontierMath, etc Long Context: @ZayneSprague
's MuSR, @realYushiBai
's LongBench, -
Debate over base model benchmarks and training data
By
–
Sure — I’m not disputing it’s an advantage, or even that counterfactually it could have been the only important thing they did. But the benchmarks we see of the base model before any stolen data would be relevant (in post-training) seem to imply otherwise
-
Cascading LLM Calls Improve Performance Efficiently
By
–
Or just any other LLM even a smol one does a great job at it – cascading to two calls helps quite a bit!
-
Token-Budget-Aware LLM Reasoning Framework for Efficiency
By
–
Token-Budget-Aware LLM Reasoning The paper proposes a framework for improving the efficiency of reasoning in large language models (LLMs) by dynamically estimating and adjusting token budgets based on problem complexity. This approach helps reduce the token overhead caused by
-
DRT-o1: Deep Reasoning Translation Optimizes Neural Machine Translation
By
–
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought Problem: Neural machine translation struggles with translating texts containing similes or metaphors, often failing to convey the intended meaning due to cultural differences and the limitations of literal
-
LearnLM: Gemini Enhanced for Personalized AI Tutoring
By
–
LearnLM: Improving Gemini for Learning An enhanced model, LearnLM, is designed to improve AI tutoring by training Gemini models to follow pedagogical instructions and adapt to diverse educational contexts. Problem: Existing generative AI systems lack tailored pedagogical
-
Align-Anything: Training Multimodal Models with Language Feedback
By
–
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback The paper introduces the Align-Anything framework to enhance all-modality models' alignment with human preferences using language feedback, improving instruction-following across text,
-
Mulberry: MLLM Reasoning via Collective Monte Carlo Tree Search
By
–
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search The paper presents Mulberry, an MLLM with step-by-step reasoning and reflection, powered by CoMCTS. CoMCTS uses collective knowledge from multiple models to efficiently
-
Reproducing o1: Reinforcement Learning Search Scaling Roadmap
By
–
Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective This paper presents a roadmap for reproducing OpenAI's o1, an advanced LLM that excels in reasoning. It focuses on four key components—policy initialization, reward design, search,