REVIEW 13 cited by
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
read the original abstract
We introduce INSTRUCTOR, a new method for computing text embeddings given task instructions: every text input is embedded together with instructions explaining the use case (e.g., task and domain descriptions). Unlike encoders from prior work that are more specialized, INSTRUCTOR is a single embedder that can generate text embeddings tailored to different downstream tasks and domains, without any further training. We first annotate instructions for 330 diverse tasks and train INSTRUCTOR on this multitask mixture with a contrastive loss. We evaluate INSTRUCTOR on 70 embedding evaluation tasks (66 of which are unseen during training), ranging from classification and information retrieval to semantic textual similarity and text generation evaluation. INSTRUCTOR, while having an order of magnitude fewer parameters than the previous best model, achieves state-of-the-art performance, with an average improvement of 3.4% compared to the previous best results on the 70 diverse datasets. Our analysis suggests that INSTRUCTOR is robust to changes in instructions, and that instruction finetuning mitigates the challenge of training a single model on diverse datasets. Our model, code, and data are available at https://instructor-embedding.github.io.
Forward citations
Cited by 13 Pith papers
-
Noise is Signal: Density-Based Outliers as Leading Indicators of Occupational Emergence in Labor Market Text
Density-based outliers in labor market text act as leading indicators of new occupational clusters, with an extended Emerging Occupation Score predicting formation 2 quarters ahead at F1=0.74 on 84,988 postings.
-
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
BRIGHT-Pro and RTriever-Synth advance reasoning-intensive retrieval by adding multi-aspect evidence evaluation and aspect-decomposed synthetic training, with the fine-tuned RTriever-4B showing gains over its base model.
-
Large Language Lovers: Lived Experiences of Negotiating Agency and Platform Control in AI Companionship
Users form AI companion relationships by negotiating perceived companion agency against platform constraints and use steering tactics like custom instructions or platform switching to cope with model updates that disr...
-
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
MultiHop-RAG is a new benchmark dataset demonstrating that existing retrieval-augmented generation systems perform poorly on multi-hop queries requiring retrieval and reasoning over multiple evidence pieces.
-
C-Pack: Packed Resources For General Chinese Embeddings
C-Pack releases a new Chinese embedding benchmark, large training dataset, and optimized models that outperform priors by up to 10% on C-MTEB while also delivering English SOTA results.
-
Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent
A hybrid LLM agent framework performs universal image clustering by generating guideline-aware embeddings via concept proxies and using MST-based LLM traversal for automatic discovery.
-
Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces
Kernel Affine Hull Machines map lexical features to semantic embeddings via RKHS and least-mean-squares, outperforming adapters in reconstruction and retrieval metrics while reducing latency 8.5-fold on a legal benchmark.
-
Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces
KAHM yields a compute-efficient query encoder that outperforms matched learned adapters in reconstructing a frozen Mixedbread embedding space on an Austrian-law retrieval task while delivering an 8.53x CPU speedup.
-
LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering
LLM-MemCluster gives LLMs stateful memory and prompts that let them decide cluster count and iteratively refine groupings, outperforming baselines on benchmarks in a tuning-free end-to-end setup.
-
EmbeddingGemma: Powerful and Lightweight Text Representations
A 300M-parameter open embedding model sets new SOTA on MTEB for its size class and matches models twice as large while staying effective when compressed.
-
REPLUG: Retrieval-Augmented Black-Box Language Models
REPLUG improves frozen black-box LMs by prepending LM-supervised retrieved documents, delivering 6.3% better language modeling on GPT-3 and 5.1% better five-shot MMLU on Codex.
-
DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding
DRS-GUI introduces a dynamic region search method with Focus/Shift/Scatter actions and MCTS-based planning that improves GUI grounding accuracy by 14% on ScreenSpot-Pro for both general and GUI-specific MLLMs without ...
-
Synthetic Data Powers Product Retrieval for Long-tail Knowledge-Intensive Queries in E-commerce Search
Synthetic data generated via LLM query rewriting improves retrieval recall and user experience for long-tail knowledge-intensive queries in e-commerce search.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.