CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning Paper • 2410.10336 • Published Oct 14 • 2
CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning Paper • 2410.10336 • Published Oct 14 • 2
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering Paper • 2410.15999 • Published Oct 21 • 19
Analysing the Residual Stream of Language Models Under Knowledge Conflicts Paper • 2410.16090 • Published Oct 21 • 7
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations Paper • 2410.18860 • Published Oct 24 • 9
A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression Paper • 2406.11430 • Published Jun 17 • 22
The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models Paper • 2404.05904 • Published Apr 8 • 8
The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models Paper • 2404.05904 • Published Apr 8 • 8
Structured Packing in LLM Training Improves Long Context Utilization Paper • 2312.17296 • Published Dec 28, 2023 • 2
Analysing The Impact of Sequence Composition on Language Model Pre-Training Paper • 2402.13991 • Published Feb 21 • 1
An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks Paper • 2210.16773 • Published Oct 30, 2022 • 1