Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models

By processing electronic health records (EHRs) as natural language sequences, large language models (LLMs) have shown potential in clinical prediction tasks such as mortality prediction and phenotyping. However, longitudinal or highly frequent EHRs often yield excessively long token sequences that result in high computational costs and even reduced performance. Existing solutions either add modules for compression or remove less important tokens, which introduce additional inference latency or risk losing clinical information. To achieve lossless compression of token sequences without additional cost or loss of performance, we propose Medical Token-Pair Encoding (MedTPE), a layered method that extends standard tokenisation for EHR sequences. MedTPE merges frequently co-occurring medical token pairs into composite tokens, providing lossless compression while preserving the computational complexity through a dependency-aware replacement strategy. Only the embeddings of the newly introduced tokens of merely 0.5-1.0% of the LLM's parameters are fine-tuned via self-supervised learning. Experiments on real-world datasets for two clinical scenarios demonstrate that MedTPE reduces input token length by up to 31% and inference latency by 34-63%, while maintaining or even improving both predictive performance and output format compliance across multiple LLMs and four clinical prediction tasks. Furthermore, MedTPE demonstrates robustness across different input context lengths and generalisability to scientific and financial domains and different languages.

Large language models process prompts by propagating activations through dozens of layers before generating a response. We ask whether the task-relevant information contained in an instruction prompt can be compressed into a single activation vector and re-injected into the model, replacing the original token sequence? We show this is achievable using a learned weighted sum of activations extracted at an intermediate layer and injected at an early layer of the target LLM. The compressed vector preserves task-relevant information, incurring an accuracy drop of under $2\%$ relative to full prompt processing. Beyond its practical implications, including reducing per-query computation for fixed instruction prompts without reprocessing the original token sequence, our analysis reveals structure in the activation space of LLMs: (i) mid-layer representations transfer meaningfully to early layers, suggesting a degree of cross-layer compatibility in how information is encoded; (ii) a single activation vector encodes a quantifiable and recoverable amount of semantic information; (iii) a weighted sum of activations is a robust representation compressor.

LLM pipelines waste substantial token budgets on low-information content: repeated context, verbose responses, and redundant boilerplate. We introduce Entropy Gate, a token compression framework applying entropy quenching $-$ a thermodynamic process that progressively freezes out low-energy tokens while preserving semantic fidelity. Each token receives a multi-factor information energy $E(t)$ combining statistical, structural, and positional components. An adaptive quenching schedule $T(τ) = T_0 / (1 + ατ)$ removes tokens whose Boltzmann survival probability $p_i = \exp(-E_i / kT)$ falls below threshold, with a fidelity gate halting compression when energy-weighted similarity drops below $θ$. We prove token selection by descending $E(t)$ maximizes expected semantic preservation, that quenching produces nested survival sets, and that achievable compression approaches the information-theoretic limit $\text{CR} \to 1 - I(P; T)/H(P)$. A Phase 1 heuristic achieves 40-60% compression across five prompt categories while maintaining $S_E > 0.80$, with energy-squared amplification $E \to E^2$ adding 10-25 percentage points. Context deduplication adds 50-70% savings on repeated blocks. Output-side quenching, motivated by findings that brevity improves accuracy, further reduces response overhead. Combined with external memory, reduction composes multiplicatively to 88-96% for agentic workloads. The framework is stateless, model-agnostic, and deploys as an OpenAI-compatible HTTP proxy.