OpenGVLab/InternVL2_5-4B
Image-Text-to-Text
•
Updated
•
3.98k
•
37
Ujita
UjitaYuri
AI & ML interests
None yet
Recent Activity
liked
a model
12 days ago
OpenGVLab/InternVL2_5-4B
liked
a model
12 days ago
meta-llama/Llama-3.3-70B-Instruct
liked
a model
12 days ago
NexaAIDev/OmniAudio-2.6B
Organizations
None yet
UjitaYuri's activity
liked
3
models
12 days ago
liked
3
models
about 1 month ago
reacted to
singhsidhukuldeep's
post with 👀
about 1 month ago
Post
1194
Exciting breakthrough in LLM reasoning: Introducing "Thread of Thought" (ThoT) - a novel prompting strategy that revolutionizes how language models handle chaotic contexts!
Unlike traditional approaches that struggle with complex, interleaved information, ThoT enables LLMs to methodically segment and analyze extended contexts with remarkable precision. Here's how it works:
Technical Deep Dive:
- ThoT employs a two-step prompting mechanism:
1. Initial Analysis: Uses a template combining chaotic context (X) and query (Q) with a trigger sentence that initiates systematic reasoning.
2. Conclusion Refinement: Leverages the organized thought sequence to extract definitive answers.
Implementation Details:
- Seamlessly integrates as a "plug-and-play" module with existing LLMs.
- Requires no model retraining or fine-tuning.
- Works with various prompting techniques and model architectures.
Performance Highlights:
- Outperformed traditional methods on PopQA and EntityQ datasets.
- Achieved 57.4% accuracy with GPT-3.5-turbo (vs. 48.2% for Chain-of-Thought).
- Demonstrated superior performance across model scales, from 7B to 70B parameters.
Key Applications:
- Retrieval-augmented generation.
- Multi-turn conversation responses.
- Complex reasoning tasks requiring information synthesis.
What makes it special: ThoT mirrors human cognitive processes by breaking down complex information into manageable segments while maintaining logical continuity – a game-changer for handling information-dense contexts.
Unlike traditional approaches that struggle with complex, interleaved information, ThoT enables LLMs to methodically segment and analyze extended contexts with remarkable precision. Here's how it works:
Technical Deep Dive:
- ThoT employs a two-step prompting mechanism:
1. Initial Analysis: Uses a template combining chaotic context (X) and query (Q) with a trigger sentence that initiates systematic reasoning.
2. Conclusion Refinement: Leverages the organized thought sequence to extract definitive answers.
Implementation Details:
- Seamlessly integrates as a "plug-and-play" module with existing LLMs.
- Requires no model retraining or fine-tuning.
- Works with various prompting techniques and model architectures.
Performance Highlights:
- Outperformed traditional methods on PopQA and EntityQ datasets.
- Achieved 57.4% accuracy with GPT-3.5-turbo (vs. 48.2% for Chain-of-Thought).
- Demonstrated superior performance across model scales, from 7B to 70B parameters.
Key Applications:
- Retrieval-augmented generation.
- Multi-turn conversation responses.
- Complex reasoning tasks requiring information synthesis.
What makes it special: ThoT mirrors human cognitive processes by breaking down complex information into manageable segments while maintaining logical continuity – a game-changer for handling information-dense contexts.
liked
2
models
about 1 month ago
upvoted
a
collection
about 1 month ago
liked
2
models
about 1 month ago
upvoted
4
papers
6 months ago
Octo-planner: On-device Language Model for Planner-Action Agents
Paper
•
2406.18082
•
Published
•
47
Complexity of Symbolic Representation in Working Memory of Transformer Correlates with the Complexity of a Task
Paper
•
2406.14213
•
Published
•
20
From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries
Paper
•
2406.12824
•
Published
•
20
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
Paper
•
2406.11833
•
Published
•
61
upvoted
4
papers
7 months ago
Octopus v4: Graph of language models
Paper
•
2404.19296
•
Published
•
116
T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
Paper
•
2405.18750
•
Published
•
21
HaLo-NeRF: Learning Geometry-Guided Semantics for Exploring Unconstrained Photo Collections
Paper
•
2404.16845
•
Published
•
6
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
Paper
•
2404.16873
•
Published
•
28