Actually I just tried something similar, which is to use the domain specific words in the first request, then go back and edit the prompt to correct their spelling. Interestingly, that didn't work — when using those terms again in the next prompt saw them misspelled.
LLMS
-
Learning Domain-Specific Language Recognition In Context
By
–
It is learning in context to recognise my domain-specific words, which I think is pretty nifty.
-
Clone Reflection-70B-llamacpp Space on Hugging Face
By
–
clone this space: https://
huggingface.co/spaces/gokaygo
kay/Reflection-70B-llamacpp?clone=true
… -
Meta Waymo USC Develop Transfusion for Multimodal AI
By
–
Scientists from @AIatMeta
, @Waymo
, and @USC develop Transfusion, a recipe combining language modeling and diffusion to train models that generate both text and image. Talk to @violet_zct directly to discover possibilities for exciting multi-modal models offered by Transfusion! -
Grok’s limitations in analyzing specific threads
By
–
The most obviously useful thing for @grok to do AFAICT would be to let me ask questions about specific threads. But AFAICT it can't do that 🙁
-
LLM-Based Agents for Software Engineering: Comprehensive Survey
By
–
10). LLM-Based Agents for Software Engineering – a survey paper on LLM-based agents for software engineering, covering perspectives ranging from requirement engineering to test generation to software maintenance.
-
RAG Noise Benchmark Measures LLM Performance Impact
By
–
8). Role of RAG Noise in LLMs – proposes a benchmark (NoiserBench) to measure how different kinds of noisy information affect RAG's performance; reports that from different kinds of beneficial noise studied (e.g., semantic, datatype, and illegal sentence), illegal sentence noise
-
LongCite Improves Long-Context Question Answering With Citations
By
–
6). LongCite – synthesizes a large-scale SFT dataset with off-the-shelf LLMs to improve long-context question answering with citations; it trains 8B and 9B parameter models that enhance citation generation capabilities from lengthy contexts while improving response correctness;
-
MemLong extends LLM context length using external retrieval
By
–
7). MemLong – utilizes an external retriever for retrieving historical information which enhances the capabilities of long-context LLMs; it consistently outperforms other SoTA LLMs on long-context benchmarks and can extend the context length on a single 3090 GPU from 4k up to
-
OLMoE: Open Sparse Mixture-of-Experts Language Model
By
–
5). OLMoE – introduces a fully-open LLM that leverages sparse Mixture-of-Experts. OLMoE is a 7B parameter model and uses 1B active parameters per input token; there is also an instruction-tuned version that claims to outperform Llama-2-13B-Chat and DeepSeekMoE 16B.