Few Shot Learning | Techlist.io

tossAug 13, 20265 min readCurated summary

Getting AI to Provide Investment Information

LLMs make it easy to generate financial content, but producing trustworthy investment information requires much more than fluent summaries. Toss Securities argues that AI must pass three gates before reaching users: selecting reliable evidence, controlling how responses are generated, and making outputs measurable and improvable. The central principle is to constrain AI autonomy where reproducibility and traceability matter, while preserving it for open-ended exploration. ## Why Investment Information Is Different - **Timeliness:** Market interpretations can change within hours due to earnings, geopolitical events, or policy news. - **Accuracy:** A company mentioned in an article may not be the company whose stock moved; it could be a subsidiary, a similarly named firm, or merely a promotional mention. - **Traceability:** Every generated claim needs supporting evidence, evaluation records, and reproducible processing. - **Non-stationarity:** Market behavior changes across earnings seasons, interest-rate events, elections, and geopolitical crises. Prompts and models tuned to one period may degrade later. LLMs and autonomous agents amplify these challenges: - LLMs can produce fluent but incorrect answers when evidence is incomplete or ambiguous. - Agents add more failure points through search, tool calls, planning, and state transitions. - Errors can propagate through different execution paths, increasing operational cost and making debugging difficult. ## Gate One: Selecting What the AI Should Say The first gate is a context-engineering process that filters and organizes evidence before it reaches the LLM. ### Classify Data at Ingestion - News, disclosures, and financial data are classified as they arrive using internally developed BERT-based models. - Metadata includes: - Taxonomy tags - Related companies and entities - Embeddings for vector search - Pre-classifying data avoids waiting until retrieval to determine whether it is relevant. ### Retrieve Broadly, Then Narrow the Candidates A hybrid retriever first prioritizes recall, after which candidates are reduced through: - **Deduplication:** Semantically similar articles are clustered so one event is not treated as many independent events. - **Reranking and filtering:** Evidence is evaluated for direct relevance to the company’s price movement. - **Taxonomy labels:** Items are categorized by explanation type, such as earnings, guidance, or corporate actions. - **Failure labels:** Promotional content, insufficient evidence, and other unsuitable sources are explicitly marked and filtered out. - **Rubrics:** Evidence is ranked according to predefined relevance criteria. ### Build Reasoning-Friendly Context The final context is arranged so the model checks: - What happened - How the event connects to the target company - Whether the evidence’s polarity matches the stock’s price direction - Whether the evidence is sufficient and current This ordering combines the filtered evidence with metadata such as the company, price direction, and time window. ## Gate Two: Controlling How Responses Are Generated The second gate limits the action space of LLMs and agents to satisfy product requirements such as cost, latency, reproducibility, and observability. ### Use Task Graphs for Clearly Defined Work Instead of leaving the entire process to an autonomous agent, Toss Securities separates it into explicit stages: - Candidate retrieval - Relevance assessment - Deduplication - Evidence construction - Final response generation Each stage has defined input and output schemas, making it a debugging and evaluation point while simplifying fallbacks and operational monitoring. ### Choose Autonomy Based on Requirement Clarity - **Autonomous agents** are useful for open-ended tasks such as discovering investment ideas or exploring possible market scenarios. - **Procedural orchestration** is better for fixed tasks, such as explaining why a specific stock moved. - Long ReAct loops increase tool calls, token usage, latency, and trace-management costs. - For structured products, deterministic pipelines let LLMs focus on summarization, rewriting, and evidence-based explanation rather than tool selection. Procedural graphs are not merely a replacement for agents. Once defined, they can become reusable tools or sub-agents that other agents call through structured interfaces, such as: ```text input: ticker, direction, time_window output: explanation, evidences, reasoning_type ``` ## Gate Three: Making the System Evaluatable Subjective judgments such as “the answer feels weak” do not provide a reliable improvement loop. The system therefore generates structured classifications alongside natural-language responses. ### Generate Rubric Categories with Each Answer - Outputs include event or reasoning types and failure categories. - Structured fields make it possible to measure: - Relevance false positives - Directional mismatches - Irrelevant evidence passing the filter - Precision, recall, and F1 score - The taxonomy must evolve as new market regimes and failure patterns appear. - Operational failures, evaluation sets, prompt versions, and model versions should be linked so improvements can be reproduced and quantified. ### Retrieve Context-Specific Few-Shot Examples Fixed few-shot examples are insufficient because event and failure types vary widely across market conditions. Instead: - Store operational samples with their decisions, failure labels, and embeddings. - Embed each new classification or verification task. - Retrieve similar positive and negative examples. - Include both successful and failed examples to show the model the decision boundary. This approach reuses production failures as future evaluation guidance and significantly improves precision and accuracy while preserving recall. Since false positives are especially damaging in investment services, filtering out unsupported explanations is more important than producing fluent text alone. ## Work Beyond Prompts and Model Training Building an investment-information AI service also requires substantial infrastructure outside the model itself: - Retrieval strategies and embedding models for finding relevant evidence - Separately trained classifiers for categorization - Evidence filtering, validation, and metadata management - Structured orchestration, monitoring, evaluation, and feedback loops The practical recommendation is to treat the LLM as one component in a controlled evidence pipeline—not as the sole decision-maker. Use autonomous agents for exploratory tasks, but rely on traceable procedural graphs, evolving taxonomies, and retrieval-based examples when the product must deliver repeatable, defensible financial information.

Read original

Few Shot Learning Large Language Models Prompt Engineering Multi Agent Systems+4

googleFeb 9, 20263 min readCurated summary

How AI trained on birds is surfacing underwater mysteries

Perch 2.0, Google DeepMind’s bioacoustics foundation model, was trained mainly on birds and terrestrial animals yet performs strongly on underwater audio. The study shows that its learned audio embeddings can support accurate whale, dolphin, reef-sound, and killer-whale classification with only a few labeled examples. This suggests that large, broadly trained bioacoustics models can transfer across environments and accelerate marine research without requiring extensive underwater training data. ## Underwater Mysteries and Bioacoustics - Ocean recordings reveal animal behavior, species distributions, and unexplained sounds. - The “biotwang,” recently attributed by NOAA to Bryde’s whales, illustrates how new calls and species identifications continue to emerge. - Google has previously developed models for humpback whales and multi-species whale detection. - Perch 2.0 extends this work despite having no underwater audio in its training data. ## Transfer Learning for Custom Classifiers - Researchers can use an existing model directly when its labels match their data. - For new sounds or datasets, transfer learning avoids training a deep neural network from scratch. - Perch 2.0 converts audio windows into compact numerical embeddings. - A logistic regression classifier is then trained on those embeddings using labeled examples. - This requires far less computation, experimentation, and training data than full neural-network training. ## Evaluation on Marine Datasets - The researchers tested Perch 2.0 with few-shot linear probes using 4, 8, 16, or 32 examples per class. - Performance was measured using ROC-AUC, where values closer to 1 indicate better class separation. - Evaluation datasets included: - **NOAA PIPAN:** Baleen-whale recordings, including minke, humpback, sei, blue, fin, and Bryde’s whales. - **ReefSet:** Reef biological sounds, fish, dolphins, anthropogenic noise, and waves. - **DCLDE:** Killer whales, humpbacks, abiotic sounds, unknown sounds, and killer-whale ecotypes. - More examples generally improved results. - ReefSet performance was already high with four examples per class for most models. - Perch 2.0 was consistently among the best-performing models across datasets and sample sizes. ## Comparisons with Other Models - Perch 2.0 was compared with Perch 1.0, SurfPerch, and Google’s multi-species whale model. - It also outperformed AVES-bird and AVES-bio on most underwater tasks. - The results show that strong underwater transfer is not limited to models trained on marine audio. ## Why Bird-Based Training Transfers to Whales - The authors suggest that large models trained on extensive datasets can generalize effectively to unfamiliar downstream tasks. - Shared acoustic patterns across animal vocalizations may allow representations learned from birds and other terrestrial species to remain useful underwater. - The findings challenge the assumption that a model must be trained directly on underwater recordings to perform well on marine classification tasks. ## Practical Tools for Researchers - Google provides a paper and a Google Colab tutorial. - The tutorial demonstrates an end-to-end workflow for building a whale-vocalization classifier. - It uses NOAA’s NCEI Passive Acoustic Data Archive and Google Cloud. - Researchers can create agile, task-specific models with relatively small labeled datasets. Perch 2.0 demonstrates that broad bioacoustic pretraining can substantially reduce the effort required to study marine sounds. Researchers can begin with general-purpose embeddings and adapt them to new whale species, calls, or underwater sound categories using only modest labeled data.

Read original

Few Shot Learning Machine Learning Foundation Models Embeddings+4

googleOct 19, 2025Original article

Teaching Gemini to spot exploding stars with just a few examples (opens in new tab)

Researchers have demonstrated that Google’s Gemini model can classify cosmic events with 93% accuracy, rivaling specialized machine learning models while providing human-readable explanations. By utilizing few-shot learning with only 15 examples per survey, the model addresses the "black box" limitation of traditional convolutional neural networks used in astronomy. This approach enables scientists to efficiently process the millions of alerts generated by modern telescopes while maintaining a transparent and interactive reasoning process. ## Bottlenecks in Modern Transient Astronomy * Telescopes like the Vera C. Rubin Observatory are expected to generate up to 10 million alerts per night, making manual verification impossible. * The vast majority of these alerts are "bogus" signals caused by satellite trails, cosmic rays, or instrumental artifacts rather than real supernovae. * Existing specialized models often provide binary "real" or "bogus" labels without context, forcing astronomers to either blindly trust the output or spend hours on manual verification. ## Multimodal Few-Shot Learning for Classification * The research utilized few-shot learning, providing Gemini with only 15 annotated examples for three major surveys: Pan-STARRS, MeerLICHT, and ATLAS. * Input data consisted of image triplets—a "new" alert image, a "reference" image of the same sky patch, and a "difference" image—each 100x100 pixels in size. * The model successfully generalized across different telescopes with varying pixel scales, ranging from 0.25" per pixel for Pan-STARRS to 1.8" per pixel for ATLAS. * Beyond simple labels, Gemini generates a textual description of observed features and an interest score to help astronomers prioritize follow-up observations. ## Expert Validation and Self-Assessment * A panel of 12 professional astronomers evaluated the model using a 0–5 coherence rubric, confirming that Gemini’s logic aligned with expert reasoning. * The study found that Gemini can effectively assess its own uncertainty; low self-assigned "coherence scores" were strong indicators of likely classification errors. * This ability to flag its own potential mistakes allows the model to act as a reliable partner, alerting scientists when a specific case requires human intervention. The transition from "black box" classifiers to interpretable AI assistants allows the astronomical community to scale with the data flood of next-generation telescopes. By combining high-accuracy classification with transparent reasoning, researchers can maintain scientific rigor while processing millions of cosmic events in real time.

Few Shot Learning AI Generative AI Gemini+4

googleSep 22, 2025Original article

Time series foundation models can be few-shot learners (opens in new tab)

Researchers at Google have introduced TimesFM-ICF, a foundation model that enables time-series forecasting to transition from zero-shot to few-shot learning via in-context fine-tuning. By utilizing continued pre-training and specialized separator tokens, the model learns to adapt to a handful of related examples at inference time without requiring the complex supervised fine-tuning typically needed for task-specific optimization. This approach effectively matches or exceeds the performance of specialized models while maintaining the flexibility of a general-purpose foundation model. ### Overcoming the Limitations of Zero-Shot Models * Traditional forecasting often requires building separate, specialized models for every unique task, which is resource-intensive and slow. * While zero-shot models like the original TimesFM provide immediate forecasts without task-specific training, they cannot incorporate relevant context, such as data from nearby sensors or similar historical patterns. * The In-Context Fine-tuning (ICF) approach allows the model to "learn" from a few examples provided at the time of prediction, similar to how Large Language Models (LLMs) use few-shot prompting. ### Architecture and the Common Separator Token * TimesFM-ICF utilizes a patched decoder architecture that tokenizes 32 contiguous timepoints into a single input token. * To prevent the model from conflating different data streams—such as separate store locations or distinct time periods—researchers introduced a "common separator token" as a digital boundary between examples. * The model processes these tokens through a transformer stack using causal self-attention (CSA), ensuring it learns from historical context without accidentally "peeking" into the future. * A shared multilayer perceptron (MLP) translates the processed output tokens back into a forecast spanning 128 timepoints. ### Performance Benchmarking and Results * The model was evaluated on 23 unseen datasets, using the Mean Absolute Scaled Error (MASE) metric to aggregate performance across diverse time-series tasks. * TimesFM-ICF demonstrated a significant performance boost over the original zero-shot TimesFM and other state-of-the-art foundation models like Moirai and Lag-Llama. * Test results showed that providing just a few in-context examples allowed the model to match the accuracy of supervised fine-tuning, which normally requires much more computational overhead and data curation. TimesFM-ICF represents a practical shift for businesses managing diverse data streams, offering a way to achieve high-accuracy forecasts by simply providing a few relevant historical examples. For those looking to optimize inventory or energy demands, this method provides the precision of a custom-tuned model with the deployment speed of a pre-trained foundation model.

Few Shot Learning AI Transformer Foundation Models+3