REVIEW 18 cited by
Large Concept Models: Language Modeling in a Sentence Representation Space
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
read the original abstract
LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for many tasks. The current established technology of LLMs is to process input and generate output at the token level. This is in sharp contrast to humans who operate at multiple levels of abstraction, well beyond single words, to analyze information and to generate creative content. In this paper, we present an attempt at an architecture which operates on an explicit higher-level semantic representation, which we name a concept. Concepts are language- and modality-agnostic and represent a higher level idea or action in a flow. Hence, we build a "Large Concept Model". In this study, as proof of feasibility, we assume that a concept corresponds to a sentence, and use an existing sentence embedding space, SONAR, which supports up to 200 languages in both text and speech modalities. The Large Concept Model is trained to perform autoregressive sentence prediction in an embedding space. We explore multiple approaches, namely MSE regression, variants of diffusion-based generation, and models operating in a quantized SONAR space. These explorations are performed using 1.6B parameter models and training data in the order of 1.3T tokens. We then scale one architecture to a model size of 7B parameters and training data of about 2.7T tokens. We perform an experimental evaluation on several generative tasks, namely summarization and a new task of summary expansion. Finally, we show that our model exhibits impressive zero-shot generalization performance to many languages, outperforming existing LLMs of the same size. The training code of our models is freely available.
Forward citations
Cited by 18 Pith papers
-
Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models
Scratchpad Patching decouples compute from patch size in byte-level language models by inserting entropy-triggered scratchpads to update patch context dynamically.
-
LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG
LatentRAG performs agentic RAG by generating latent tokens for thoughts and subqueries in one forward pass, matching explicit methods' accuracy on seven benchmarks while reducing latency by ~90%.
-
Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech
Progressive LLM-initialized training plus teacher-student distillation yields omnilingual sentence embeddings that halve FLORES error and cut BIBLE error 15× while supporting speech and zero-shot Spectrum transfer.
-
Training Large Language Models to Reason in a Continuous Latent Space
Coconut lets LLMs perform reasoning directly in continuous latent space by recycling hidden states as inputs, outperforming standard chain-of-thought on search-intensive logical tasks with better accuracy-efficiency t...
-
From Found to Designed: Concepts as a Design Axis for Large Language Models
Concept-aware LLM interventions can be mapped by whether concepts are internally induced or externally grounded and by pipeline stage, revealing inference-time methods as the most underexplored cell.
-
From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models
Masked diffusion language models fail to exploit their any-order interface because of positional uncertainty; insertion-based (FlexMDM) and latent-segment (LatentMDM) variants recover distinct any-order inference beha...
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing l...
-
Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs
Four axioms (Causality, Minimality, Separability, Stability) are formalized for latent thought representations; audits of open LLMs on 23 tasks show none satisfy all four and representations add little beyond input em...
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
-
Concept Tokens: Learning Behavioral Embeddings Through Concept Definitions
A single token embedding trained on concept definitions can directionally steer a frozen LLM's behavior, but hallucination gains come mainly from abstention and new factual details are not reliably stored.
-
Controllably Efficient Language Models
A single transformer variant can compress past context into chunk summaries and use chunk size as a test-time knob to trade quality against speed and memory, outperforming many efficient baselines on recall benchmarks.
-
Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection
RAF, resolution-adaptive federated learning, uses multi-resolution knowledge distillation to stop resolution differences between clients from degrading federated keypoint detection.
-
From Found to Designed: Concepts as a Design Axis for Large Language Models
Concepts should be an explicit design axis for LLMs, organized by pipeline stage and internal-vs-external origin, rather than recovered post-hoc.
-
Forewarned is Forearmed: When Non-Sequential Embedding Turns Into an Anomaly Detector
Certain dimensions in SONAR sentence embeddings act as anomaly detectors by measuring consistency between successive encoding and decoding.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
A 22M-parameter hyperbolic model answers structured EHR questions with accuracy close to LLM-based systems (EHRXQA 89.5%, MIMIC-Instr 76.0%).
-
Synergy: End-to-end Concept Model
A byte-level transformer with a learned top-k router matches a tokenized Llama3 baseline on Wikipedia bits-per-byte, and works best when positional encoding is removed from its middle layers.
-
Mimir: Large-scale Multilingual Concept Modeling
Mimir is a 1.6B multilingual concept model pretrained on 38.9 billion sentences across 46 languages and instruction-tuned on 66.8 million sentences across 35 languages, then compared to a token-based LM of similar size.
-
On The Landscape of Spoken Language Models: A Comprehensive Survey
A literature survey that organizes spoken language models by architecture, training, and evaluation choices and identifies key challenges and future directions.
Discussion (0). Sign in to comment.