All bites
The whole library, newest first. Filter by what you are here for, or pick a topic if you already know.
8664 bites
Page 31
How Transformers encode token position
Attention is permutation-invariant, so positional encodings (sinusoidal, learned, or rotary) are added or applied.
Self-attention and the Query, Key, Value matrices
Queries score against keys via scaled dot product, softmax yields weights, and those weight the values into the output.
Why RAG persists despite million-token context windows
Cost and latency scale with context, attention degrades in the middle, and RAG adds freshness, access control, and citations.
Designing an autonomous research-and-report agent
Planner that decomposes goals, short-term scratchpad plus long-term vector memory, structured tool calls, and a reflect-retry loop for error correction.
Data lineage and machine unlearning for a fine-tuned LLM
Version and fingerprint datasets, record transforms and which checkpoint saw what, and enable unlearning via retraining, data sharding, or approximate gradient methods.
Practical explainability for an LLM loan summary
Use attribution-by-design with grounded citations, structured rationales, and a deterministic rules layer instead of slow per-token SHAP.
Measuring fairness in an embedding-based text classifier
Define group definitions, apply demographic parity and equalized odds, and address noisy labels and implicit group membership.
Preprocessing conversations to protect privacy before fine-tuning
Detect and redact PII with NER plus regex, choose redaction versus pseudonymization, and validate recall.
Mitigating demographic bias in a fine-tuned chatbot
Curate or counterfactually augment training data to balance demographics, plus apply post-hoc guardrails or fairness-constrained fine-tuning.
Handling outlier activations in INT8 quantization
Profile activation magnitudes to find a few large-magnitude outlier channels, then keep those in higher precision while quantizing the rest, a mixed-precision decomposition.
Dynamic batching and the throughput-latency trade-off
The server groups concurrent requests into one batch to use the GPU fully, but larger batches and waiting to fill them raise per-request latency and time to first token.
Detecting catastrophic forgetting in continual fine-tuning
Maintain a frozen held-out benchmark of original capabilities, evaluate after every fine-tune, track per-capability deltas, and alert on regressions.
Agent planning beyond a ReAct loop
ReAct adapts step by step but costs many calls, plan-then-execute drafts a full plan upfront for fewer calls but is brittle to surprises, hierarchical decomposition splits goals…
Evaluating a multi-tool LLM agent
Measure end-to-end task success, plus trajectory quality like correct tool choice and arguments, efficiency via steps and cost, and robustness to errors and edge cases.
Chunking and embedding a RAG corpus
Choose chunk size and overlap balancing context vs precision, prefer semantic boundaries, then pick an embedding model matching domain and dimension, and store with metadata.
When to choose RAG over fine-tuning
RAG for fresh, factual, citable knowledge that changes often, fine-tuning for behavior, style, or format the model must internalize.
Diagnosing sycophancy from RLHF
Annotators reward agreeable, inoffensive answers so the reward model learns to favor them, fix by diversifying labelers, rewarding factual correctness over agreeableness, and…
Fixing a prompt that ignores key constraints
Move the critical constraint to a prominent position, state it positively and specifically, separate instructions from data with delimiters, and add a concrete example.
Encoder, decoder, and encoder-decoder Transformers
Encoder-only uses bidirectional masked-token pretraining for understanding tasks, decoder-only uses causal next-token prediction for generation, encoder-decoder uses span corruption for…
Static vs contextual word embeddings
Static embeddings give one fixed vector per word ignoring context, contextual ones vary by sentence and resolve polysemy at higher compute cost.