REVIEW 25 cited by
Generative Representational Instruction Tuning
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
Generative Representational Instruction Tuning
read the original abstract
All text-based language problems can be reduced to either generation or embedding. Current models only perform well at one or the other. We introduce generative representational instruction tuning (GRIT) whereby a large language model is trained to handle both generative and embedding tasks by distinguishing between them through instructions. Compared to other open models, our resulting GritLM 7B sets a new state of the art on the Massive Text Embedding Benchmark (MTEB) and outperforms all models up to its size on a range of generative tasks. By scaling up further, GritLM 8x7B outperforms all open generative language models that we tried while still being among the best embedding models. Notably, we find that GRIT matches training on only generative or embedding data, thus we can unify both at no performance loss. Among other benefits, the unification via GRIT speeds up Retrieval-Augmented Generation (RAG) by > 60% for long documents, by no longer requiring separate retrieval and generation models. Models, code, etc. are freely available at https://github.com/ContextualAI/gritlm.
Forward citations
Cited by 25 Pith papers
-
IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions
IdioLink introduces a benchmark dataset and evaluation showing that strong embedding models struggle to retrieve equivalent meanings across idiomatic and literal forms, relying on shallow cues instead.
-
Test-Time Compute for Frozen Embedding Models through Agentic Program Search
Agentic program search over frozen embedding APIs yields a parameter-free inference algebra—a softmax-weighted centroid of top-K documents interpolated with the query—that lifts nDCG@10 across seven model families on ...
-
Test-Time Compute for Frozen Embedding Models through Agentic Program Search
A softmax-weighted centroid of the local top-K documents interpolated with the query improves nDCG@10 for frozen embedding models across seven families on held-out BEIR data.
-
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.
-
Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval
ARK adaptively retrieves from knowledge graphs using global lexical search and one-hop neighborhood exploration, reaching 59.1% Hit@1 on STaRK with up to 31.4% gains over training-free baselines and enabling distillat...
-
UEmbed: Unified Sparse and Dense Multimodal Embeddings
UEmbed uses 16 special tokens over a partitioned vocabulary to make a decoder-only multimodal model emit dense and sparse embeddings in one forward pass; the 9B model scores 71.8 dense / 71.0 sparse on MMEB-v2.
-
FiRE: Enhancing MLLMs with Fine-Grained Context Learning for Complex Image Retrieval
Disentangled fine-grained context then retrieval fine-tuning on an 87K auto-generated quintuple CIR dataset lifts a 4B MLLM past larger universal retrievers on complex zero-shot image search.
-
Semantic Retrieval for Product Search in E-Commerce
A dual-encoder LLM is trained via contrastive learning then ROAR to retrieve exact matches and rank substitutes in e-commerce search.
-
Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs
LRD framework with Frenet, NRS, and GFMI metrics shows layer-wise structure in 31 models provides usable signal for model selection and pruning on MTEB tasks.
-
Test-Time Compute for Frozen Embedding Models through Agentic Program Search
Agentic program search over a frozen encoder API yields retrieval programs that improve nDCG@10 on held-out tasks and unseen encoder families with no per-domain training.
-
Reproducing Complex Set-Compositional Information Retrieval
Neural retrievers that double BM25 performance on QUEST collapse below 0.02 Recall@100 on the new LIMIT+ benchmark while lexical methods reach 0.96, with all methods degrading as compositional depth increases.
-
Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA
Rabtriever distills a generative reranker into an efficient bi-encoder using on-policy JEPA to achieve near-reranker accuracy with linear complexity on rationale-based retrieval.
-
Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA
Rabtriever distills a generative reranker into an efficient independent encoder using JEPA and auxiliary reverse KL loss to achieve linear complexity and strong performance on rationale-based retrieval tasks.
-
Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI
EAVAE disentangles style from content via contrastive pretraining and an explainable discriminator in a VAE setup, claiming SOTA authorship attribution on multiple datasets and strong few-shot AI text detection.
-
Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
LLMs exhibit mid-layer representation advantage for recommendations; MARC compresses representations modularly to reduce costs while improving performance, as shown in a large-scale online advertising deployment.
-
ViLL-E: Video LLM Embeddings for Retrieval
ViLL-E introduces a dynamic embedding mechanism and joint contrastive-generative training for VideoLLMs, delivering up to 7% gains in temporal localization and 4% in video retrieval while enabling new zero-shot capabilities.
-
OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
Dynamic hierarchical data pruning improves NDCG@10 and Recall@20 for dense retrievers while reaching full performance in half the iterations.
-
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.
-
Should We Still Pretrain Encoders with Masked Language Modeling?
Controlled ablations of 38 models find MLM superior to CLM on representation benchmarks while CLM offers better data efficiency and stability; a biphasic CLM-then-MLM schedule is optimal under fixed compute and improv...
-
DataComp-LM: In search of the next generation of training sets for language models
DCLM-Baseline dataset lets a 7B model reach 64% 5-shot MMLU accuracy after 2.6T tokens, beating prior open-data models by 6.6 points on MMLU with 40% less compute.
-
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
-
StarCoder 2 and The Stack v2: The Next Generation
StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.
-
SHIFT: Self-reconstruction Harnesses Implicit Fine-grained Thinking for Retrieval
SHIFT trains LLM retrievers to reason through latent continuous tokens and reconstruct explicit reasoning traces, improving reasoning-intensive retrieval.
-
Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model
Qwen3-embedding models show noise sensitivity in conversational retrieval where dialogue artifacts rank highly despite lacking semantic value, a problem reduced by query prompting and more severe than in prior Qwen ve...
-
MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching
MLT-Dedup achieves 91% reduction in online video repetition rates at 90% precision and 5x indexing capacity using multi-level representations and differential feature-enhanced similarity on a real-world platform.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.