On Memorization of Large Language Models in Logical Reasoning
Paper
•
2410.23123
•
Published
•
18
SimulBench
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
SimulBench's activity
yuchenlin
authored
a
paper
about 2 months ago
KikiQiQi
updated
a
Space
3 months ago
yuchenlin
authored
4
papers
6 months ago
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Paper
•
2406.18495
•
Published
•
12
MantisScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation
Paper
•
2406.15252
•
Published
•
14
WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
Paper
•
2406.11069
•
Published
•
13
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Paper
•
2406.08464
•
Published
•
65
KikiQiQi
updated
a
dataset
7 months ago
yuchenlin
authored
a
paper
7 months ago
Post
2385
Introducing **BaseChat**!
https://huggingface.co./spaces/allenai/BaseChat_URIAL
This is a demo for our URIAL paper that enables base LLMs to chat with in-context alignment. You can talk directly with base, untuned LLMs to find out what knowledge and skills they have already learned from pre-training instead of SFT or xPO or RLHF. Also, you can use this to explore the pre-training data of base LLMs by chatting! I found a very interesting case: Base version of Llama-3-8B often thinks it is built by OpenAI, lol.
https://huggingface.co./spaces/allenai/BaseChat_URIAL
This is a demo for our URIAL paper that enables base LLMs to chat with in-context alignment. You can talk directly with base, untuned LLMs to find out what knowledge and skills they have already learned from pre-training instead of SFT or xPO or RLHF. Also, you can use this to explore the pre-training data of base LLMs by chatting! I found a very interesting case: Base version of Llama-3-8B often thinks it is built by OpenAI, lol.
KikiQiQi
updated
3
datasets
7 months ago
yuchenlin
authored
a
paper
8 months ago
yuchenlin
authored
a
paper
9 months ago
KikiQiQi
updated
2
datasets
10 months ago
yuchenlin
authored
4
papers
10 months ago
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
Paper
•
2403.02502
•
Published
•
3
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
Paper
•
2402.08983
•
Published
•
2
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
Paper
•
2402.14658
•
Published
•
82
L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Paper
•
2402.09052
•
Published
•
17