enterprise chatbot developers

Abstract: Large language models (LLMs) now serve as the backbone of agents that reason over many turns, call tools, and pursue long-horizon tasks. To avoid recomputation, a model stores the attention keys and values of all past tokens in a key-value (KV) cache. Each layer maintains its own cache, so KV-cache memory can become the main bottleneck for GPU serving. Most compression methods operate within a single layer, by quantizing the cache entries, reducing the channel dimension, or evicting less important tokens. All three lose substantial accuracy at high compression ratios. Cross-layer methods share one compressed cache across adjacent layers to go beyond this limit. However, these methods also degrade sharply at high compression ratios. We find that the KV-cache representations of adjacent layers are quite different, whereas the input hidden states of adjacent layers are highly similar. We also find that, under the same memory budget, reducing the dimension of this shared latent loses far more accuracy than quantizing it. Based on these findings, we propose BellowsKV, a training-free method that maps the hidden states of n adjacent layers to one shared latent per token. At inference time, each layer reads its own keys and values from this latent through a layer-specific projection. We keep the latent at full dimension and compress it in two other ways: BellowsKV-Quant stores the latent at low precision, which is nearly lossless because the latent has no dominant outlier channels; BellowsKV-Evict makes one shared eviction decision per block, because the layers rank token importance very similarly. Across Llama-3.1-8B, Mistral-7B and Qwen2.5-7B, BellowsKV-Quant retains about 99% of full-cache accuracy at 3.6x compression and 97-98% at 13-14x, where the strongest cross-layer method retains at most 84% at 16x. Code: https://github.com/MorrisZJ/BellowsKV

Abstract: Multimodal knowledge graphs (MMKGs) organize information across different modalities to support multimodal Graph Retrieval-Augmented Generation (RAG), which aims to improve the performance of multimodal large language models (MLLMs). The effectiveness of these multimodal Graph RAG methods largely depends on the quality of the constructed MMKGs. However, most existing methods construct MMKGs without explicit guidance on graph quality, while reinforcement learning (RL)-based methods that rely on final-answer correctness may provide only indirect feedback on MMKG quality. To address these limitations, we propose MMKG-R1, a novel MMKG-quality-driven RL framework for training an MLLM as a multimodal knowledge constructor. To be specific, MMKG-R1 introduces multiple quality-aware rewards to directly evaluate both the quality of information extracted from individual knowledge sources and the quality of the assembled MMKG. These rewards are then used to guide the RL training. Experiments across multiple datasets show that MMKG-R1 constructs MMKGs that improve downstream question-answering accuracy.

Abstract: A large language model can only use the text that fits in its context window, and it recomputes its internal key-value (KV) state for a prompt every time the prompt is sent. We test a memory layer, the public package galahad-kv, that saves the KV state of each block of about 16,000 tokens to encrypted local NVMe disk and loads it back later, byte-exact, without recomputing it. We ran it on 50,000,000 tokens of real public text, served through vLLM on one NVIDIA H100, with Gemma 4 12B and Gemma 4 31B. Every block we probed was loaded back from the encrypted store with no recompute (100 of 100, at depths from 0 to 50M tokens) on both models. Loading a block was 2.8x to 4.3x faster than recomputing it and used 8.8x to 12.3x less GPU energy, and GPU memory stayed flat over the whole 50M-token stream. Asked about facts planted millions of tokens earlier, the 12B model gave the right answer 82 times out of 100 and the 31B model 98 times out of 100. Neither model made up an answer. The limits are as follows. This is reuse of stored state, not a wider attention window: one block is loaded at a time, and how well a question is answered depends on the model. Writing the memory is a one-time cost, and the store takes terabytes of local NVMe disk. We describe the test protocol, which is built to resist common ways of gaming long-context benchmarks, and give a single-GPU reproduction that uses public software and a free licence for the package.

Abstract: Zero-shot classifiers are useful for routing user requests to specialized LLM tasks, but scoring every request against a large candidate set is expensive: a zero-shot NLI classifier must evaluate one premise-hypothesis pair per label, so cost scales linearly with taxonomy size. We study a student-guided teacher distillation pipeline for a fixed taxonomy of 60 LLM task categories: a compact ModernBERT classifier predicts the full category distribution in one forward pass and retrieves a small top-k candidate set, and a larger DeBERTa-v3 zero-shot NLI classifier reranks only those candidates rather than all 60 labels; the resulting teacher labels iteratively improve the student, which produces sharper candidates for the next round. Unlike generic embedding retrieval or clustering-derived shortlists used in extreme multi-label classification, our candidate generator is trained end-to-end on the target taxonomy and is the same model serving production traffic, distinguishing it from LLM-routing work that routes between candidate models, and from concurrent System-1 encoder-classifier proposals (e.g. TypeSafe AI's Jev and the open-source Laya project) whose training methodology is undocumented or RL-based. Our best student checkpoint reaches 77.5% teacher agreement on a 200-example evaluation set, and preliminary coverage measurements show Coverage@16 of 91-100%, suggesting top-k sets retain most of the teacher's decision-relevant information. We further show truncated top-k teacher scores should not be treated as full 60-class soft targets for KL distillation: zeroing untruncated classes destroys the dark knowledge soft-label distillation depends on, introducing systematic bias rather than a harmless sparse approximation. A complete evaluation, including coverage at multiple k on a held-out set, an embedding-retrieval baseline, and a larger human-reviewed test set, remains in progress.

Abstract: Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods improve how source content is accessed and organized, while agent-memory systems preserve reusable knowledge from prior interactions, but repeated use of the same source is still largely treated as repeated access rather than an opportunity to progressively improve understanding of that source. We study source learning: developing reusable source-specific competence over a persistent authoritative source. We represent this competence with a persistent source model that captures reusable understanding of the source, including how its knowledge is structured, interpreted, and applied. To construct and progressively refine such models, we propose SourceLearn, which combines two complementary learning mechanisms. Self-Directed Source Learning identifies what remains incompletely understood and adaptively revisits the source, while Task-Guided Source Learning uses downstream experience to reveal local representational gaps and recurring needs in how source knowledge should be organized. In both cases, learning signals determine what should be reconsidered, while persistent updates are reconstructed from the authoritative source. Across five benchmarks and three LLM backends, SourceLearn achieves the best performance in 13 of 15 settings, with gains of up to 22.6 points over Hybrid RAG and substantial overall improvements over static source representations and experience-based memory baselines.

Abstract: Persistent textual memory allows language models to carry information across long interactions, but learning what to remember is fundamentally a credit-assignment problem. A memory rewrite may only become useful many steps later, while much of the observed utility may be inherited from information already stored before the rewrite. We introduce Memory Gain Policy Optimization (MGPO), which isolates the incremental value of each memory rewrite by crediting it for its marginal contribution to current and future downstream utility. This turns delayed memory utility into a direct learning signal for optimizing what information should persist. We study MGPO on document-level information extraction, where structured supervision makes the effects of individual memory updates directly measurable. MGPO improves extraction while reducing average memory length by nearly 80% relative to the initial memory policy before optimization. The learned memory policy also supports reuse and transfer across domains, downstream models without further training. These results show that effective memory learning depends not only on preserving useful information, but on identifying which memory updates create lasting incremental value.

Abstract: We consider persistent LLMs that accumulate memories of their interactions with a user over time. Such LLMs maintain memories using external storage, which they can query to overcome the limitations of a fixed context window. Such systems have numerous practical applications, as they can draw on all past interactions when responding to user queries. In this paper, we ask whether LLMs can forget information shared with them upon a user's request. We find that current LLMs fail to delete such information---even when they claim to have forgotten it and even when operating with a limited context. To this end, we consider a new direction of study: Deletion of LLM Memories. We show that naively removing messages that match a user's deletion request is insufficient, since conversations naturally introduce message dependencies that cause information to persist. To correctly handle deletion requests, we propose the DeLLM framework. It dynamically constructs relevant context for each LLM query and maintains a provenance graph of messages to determine which ones must be removed during deletion. Our experiments show that DeLLM achieves a high deletion rate while maintaining utility.

Abstract: Reliable confidence estimation is essential for large language model deployment. However, answer-level calibration remains challenging because generation errors are often localized: a response may be fluent and high-probability overall while still failing at a critical number, entity, or factual claim. Existing estimators compress token probabilities, sequence likelihoods, entropy, or beam statistics into a global score, which can dilute such local risk signals. We propose TRACE, a single-pass, decoded-answer-preserving confidence estimator that treats decoding-time uncertainty as a trajectory through three steps: (i) recording token-level surprisal and predictive entropy during decoding, (ii) applying local risk operators to preserve uncertainty spikes, and (iii) converting localized trace risk into answer-level confidence. TRACE produces a label-free risk score, while TRACE+ calibrates trace-only features into probabilities using a held-out split, without extra generations or external verifiers. We evaluate four tasks against 19 calibration baselines, and TRACE+ reduces Brier from 0.149 to 0.137 and improves AUROC from 0.758 to 0.792 over the strongest likelihood baseline. Across seven LLMs, TRACE+ improves over the best non-TRACE baseline pool from 0.136 to 0.120 Brier and from 0.764 to 0.817 AUROC. Results show that localizing decoding-time risk provides a general approach to calibration.

Abstract: Retrieval-augmented generation (RAG) improves knowledge-intensive large language model (LLM) applications by conditioning generation on retrieved documents, but longer contexts increase latency, key-value (KV) cache memory, and token cost. Post-retrieval compression can reduce this cost, yet existing compressors often operate independently for each query, rely on auxiliary models or rewriting, and introduce online overhead that can offset the benefit of shorter prompts. We revisit RAG compression from a data-mining perspective by aggregating historical query--document--model interactions into reusable evidence views. We first show that modern compressors have unstable gains over simple truncation and can add substantial inference-time latency. We then propose Reusable Evidence View Aggregation (REVA), a framework that mines the target generator's historical attention traces into a document-keyed, budget-agnostic score store. REVA maps token-level attention to readable word units, aggregates importance across repeated document accesses, and renders budget-specific plain-text views that preserve document order and the standard RAG interface. Across four representative benchmarks and modern LLMs, REVA improves generation quality by 1.0--5.8 points over existing advances, while reducing compression overhead by a factor of 5.3 to 15.6, adding less than 40 ms of latency.

Abstract: Large Language Models (LLMs) are increasingly deployed with hierarchical instructions, yet they remain vulnerable to conflicts in which user directives override system-level constraints. Existing defense mechanisms predominantly focus on static input inspection and therefore fail to detect Response Drift, a phenomenon in which the model's final response violates system-level constraints despite seemingly compliant inputs. To bridge this gap, we introduce ELCD, a response-level latent conflict detector for post-generation, pre-delivery verification. Given the full generated output, ELCD constructs a composite hidden-state representation by concatenating the final-token embedding with the mean-pooled response embedding. It then optimizes a pairwise margin ranking objective to separate compliant and drifting responses in latent space. Extensive experiments across five mainstream LLMs ranging from 1.5B to 14B parameters demonstrate that ELCD significantly outperforms competitive baselines. Notably, it improves the PR-AUC on Llama-2-7B by approximately 30 percentage points and reduces the False Positive Rate at 95% TPR (FPR95) on Mistral-7B to 2.67%. These results suggest that ELCD provides a promising approach for latent instruction-conflict detection in open-weight or self-hosted LLM deployments.