Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive agent behavior, it remains an open-problem to correctly relate language underst…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “instruction following”
Study shows model size inversely affects few-shot instruction accuracy.
problem Understanding how model size impacts few-shot instruction prompting accuracy.
method Introduced DeltaWords dataset to evaluate model's ability to follow instructions.
result Model size inversely affects few-shot instruction accuracy, with larger models performing worse.
Learning in environments with large state and action spaces, and sparse rewards, can hinder a Reinforcement Learning (RL) agent's learning through trial-and-error. For instance, following natural language instructions on the Web (such as booking a flight ticket) leads to RL settings where input vocabulary and number of…
This paper proposes a new method to connect language and physical actions in reinforcement learning.
problem Connecting linguistic representations to the physical world in embodied agents.
method Language-conditioned goal generators to decouple sensorimotor learning from language acquisition.
result Agents can demonstrate a diversity of behaviors for any given instruction.
Improved robot navigation using multi-head attention for natural language instructions.
problem Improving robot navigation in unfamiliar environments.
method Proposes a multi-head attention mechanism blending layer in a neural network model.
result Significant performance gains in translating instructions for unseen environments.
New RL framework learns task completion without prior knowledge.
problem Learning task completion without linguistic or perceptual knowledge.
method Sequentially imagining visual goals and choosing actions.
result Framework outperforms flat and hierarchical architectures.
WebGUM learns web navigation from multimodal data, outperforming previous methods.
problem Limited generalization from domain-specific models in web navigation.
method Instruction-following multimodal agent trained on vision-language foundation models.
result Significant improvement in web navigation performance on benchmarks.
Qwen3-8B outperforms classical models in financial text classification.
problem Financial text classification for trading systems and sentiment analysis.
method Noisy Embedding Instruction Finetuning and Rank-stabilized Low-Rank Adaptation.
result Qwen3-8B achieves better classification accuracy and fewer training epochs.
LLM Pro Finance Suite enhances financial NLP with instruction-tuned models.
problem Limited NLP capabilities for financial tasks in generalist models.
method Instruction-tuned large language models fine-tuned on financial data.
result Consistent improvement over state-of-the-art baselines in finance tasks.
Method constructs finance LLMs without instruction data using pretraining and model merging.
problem Developing domain-specific LLMs for finance is resource-intensive.
method Continual pretraining on financial data + model merging of instruction-tuned and domain-specific pretrained vectors.
result Successfully constructs instruction-tuned LLMs for finance without additional instruction data.
Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a given symbolic instruction. Final goals are specified to our agent via images o…
Interactive learning with hindsight instruction feedback achieves better performance than traditional methods.
problem Learning with expert supervision of optimal responses is often impractical or requires expert knowledge.
method Study of interactive learning with hindsight instruction feedback, introducing LORIL algorithm.
result LORIL algorithm achieves regret, improving over baselines in domains with low-rank instruction-response distribution.
In this paper, we propose a framework that enables a human teacher to shape a robot behaviour by interactively providing it with unlabeled instructions. We ground the meaning of instruction signals in the task-learning process, and use them simultaneously for guiding the latter. We implement our framework as a modular …
A method to improve LLMs by automating the construction of a mixture of expert prompts.
problem Limitation of single instruction prompts in covering complex problem spaces.
method Divide the problem space into sub-regions, each governed by a specialized expert with both an instruction and demos. A two-phase process constructs these experts.
result Achieves an average win rate of 81% across major benchmarks.
Improved financial sentiment analysis using simple instruction tuning of LLMs.
problem Lack of accurate financial sentiment analysis by large language models.
method Instruction tuning of general-purpose LLMs with a small portion of financial sentiment data.
result Significant improvement in financial sentiment analysis, especially in complex scenarios.
Improves matrix multiplication throughput for asymmetric bit-width operands.
problem Matrix multiplications between asymmetric bit-width operands, especially 8- and 4-bit, are not efficiently handled by existing SIMD instructions.
method Proposes a new SIMD matrix multiplication instruction that uses mixed precision on inputs (8- and 4-bit) and accumulates into 16-bit output, improving throughput.
result Offers 2x improvement in throughput compared to existing symmetric-operand-size instructions, with negligible overflow.
Advanced AI model predicts stock movements post earnings reports.
problem Inaccurate stock predictions from earnings reports.
method Fine-tuned LLMs with QLoRA compression, integrating financial and market data.
result Significantly improved predictive accuracy compared to benchmarks.
Paper fine-tunes LLaMA-3-8B for financial NER using instruction and LoRA.
problem LLMs struggle with financial NER, especially differentiating entities and amounts.
method Instruction fine-tuning combined with LoRA for parameter-efficient learning.
result Micro-F1 score of 0.894 on financial NER tasks, outperforming other models.
RAG-IT automates financial analysis using LLMs and specialized datasets.
problem Manual financial analysis is time-consuming and requires expertise.
method Retrieval-Augmented Instruction Tuning (RAG-IT) fine-tunes an LLM for financial tasks.
result RAG-IT improves financial report generation performance compared to commercial systems.
CoE modularizes LLMs for scalable, cost-effective AI systems.
problem Challenges in scalability, cost, and customization of monolithic LLMs.
method Composition of Experts (CoE) leverages multiple expert LLMs with a router for dynamic selection.
result CoE achieves superior performance with reduced computational overhead and cost.
Enhances LLMs for predicting stock movements by considering news dissemination and context.
problem Lack of consideration for news dissemination and insufficient contextual data in LLMs for stock price prediction.
method Clusters news for reach assessment, enriches prompts with specific data and instructions, fine-tunes an LLM using the dataset.
result Improves prediction accuracy by 8% compared to existing methods.
FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasetscs.CL
This paper benchmarks FinGPT for financial datasets using open-source large language models.
problem Challenges in integrating GPT-based models with financial datasets.
method Instruction Tuning paradigm for open-source large language models adapted for financial contexts.
result Demonstrates the effectiveness and adaptability of FinGPT in financial tasks.
SymNoise improves language model fine-tuning by 6.7% over NEFTune, using symmetric noise.
problem Improving performance of language models through noise-based fine-tuning.
method Introducing SymNoise, a new fine-tuning method using symmetric noise in embeddings.
result SymNoise increases model performance by 69.04% on AlpacaEval compared to NEFTune's 64.69%.
InvestLM is a financial domain LLM tuned on LLaMA-65B for investment advice.
problem Improving financial text understanding and advice generation for investment.
method Curated financial instruction dataset, LLaMA-65B, less-is-more-for-alignment approach.
result InvestLM provides comparable responses to state-of-the-art commercial models.
Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networkscs.DC
Predicting the number of clock cycles a processor takes to execute a block of assembly instructions in steady state (the throughput) is important for both compiler designers and performance engineers. Building an analytical model to do so is especially complicated in modern x86-64 Complex Instruction Set Computer (CISC…
Paper proposes a curriculum for RL agents to learn from expert demonstrations.
problem Training RL agents efficiently from expert demonstrations.
method Develops a training curriculum that starts from the goal and works backwards.
result Improves sample efficiency for some tasks compared to PPO.
Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a…
Neuro-symbolic agent learns systematic generalisation from formal instructions.
problem Achieving zero-shot generalisation of formally specified tasks.
method Combines deep reinforcement learning with temporal logic.
result Systematic learning emerges with convolutional layers and abstract operators.
Framework learns useful subgoals from demonstrations and instructions.
problem Efficient long-term planning for novel goals.
method Rational subgoals (RSGs) learned from demonstrations and task descriptions.
result Improves performance-time efficiency of planning algorithms.
Training-free looped transformers improve model performance without additional training.
problem Improving model performance without additional training or fine-tuning.
method A lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen checkpoint without additional fine-tuning.
result Our method improves model performance across various model families.
The study examines label smoothing to improve confidence calibration in fine-tuned LLMs.
problem Improving confidence calibration in fine-tuned large language models (LLMs) after instruction tuning.
method Examine various open-sourced LLMs, label smoothing, and custom kernel design.
result Label smoothing is effective in maintaining confidence calibration but faces challenges in large vocabulary LLMs.
To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge f…
Efficient FPGA virtualization for deep learning reduces user isolation and overhead.
problem Poor isolation and heavy re-compilation overhead in FPGA-based DNN accelerators.
method Two-level instruction dispatch module, multi-core hardware resources pool, tiling-based instruction frame package, two-stage static-dynamic compilation.
result 1.07-1.69x and 1.88-3.12x throughput improvement over previous designs.
In2Core selects a coreset for efficient LLM fine-tuning with reduced data.
problem Costly fine-tuning of large language models due to extensive parameters and data requirements.
method Analyzes model gradients to estimate training sample influence, optimizing for efficiency.
result Achieves similar performance with 50% of training data using In2Core.
BTZSC benchmarks zero-shot text classification across diverse models.
problem Systematically comparing zero-shot text classification across various models.
method Comprehensive benchmark of 22 datasets, comparing NLI cross-encoders, embedding models, rerankers, and instruction-tuned LLMs.
result Rerankers and instruction-tuned LLMs outperform NLI cross-encoders, with rerankers setting a new state-of-the-art.
New models avoid lookahead bias by training on past data only.
problem Lookahead bias in language models.
method Chronologically consistent training on data before a knowledge-cutoff date.
result Elimination of lookahead bias in predictions.
We are increasingly surrounded by artificially intelligent technology that takes decisions and executes actions on our behalf. This creates a pressing need for general means to communicate with, instruct and guide artificial agents, with human language the most compelling means for such communication. To achieve this i…
Learning color mixing is difficult for novice painters. In order to support novice painters in learning color mixing, we propose a prediction model for semitransparent pigment mixtures and use its prediction results to create a Smart Palette system. Such a system is constructed by first building a watercolor dataset wi…
TRIPLE efficiently optimizes prompts with a budget constraint.
problem Efficiently selecting good prompts from a pool of candidates.
method TRIPLE connects prompt optimization to best arm identification in MAB, leveraging BAI-FB tools.
result TRIPLE outperforms baselines on multiple tasks with limited budget constraints.
VALAN is a framework for navigation agents in photo-realistic environments.
problem Developing agents for indoor navigation tasks.
method Deep reinforcement learning with SEED RL architecture.
result VALAN framework can solve a variety of RL problems.
Study reveals LLM personality patterns but lacks behavioral consistency.
problem Understanding and validating personality traits in LLMs.
method Characterized LLM personality across three dimensions: training dynamics, self-report validity, and intervention effects.
result Self-reported traits do not reliably predict behavior, and instructional alignment affects trait expression but not behavior.
Study shows multilingual LLM calibration effects improve model confidence but not accuracy.
problem Improving multilingual language model calibration in low-resource settings.
method Analysis of two multilingual benchmarks using instruction-tuning and label smoothing.
result Model confidence increases in low-resource languages after instruction-tuning but accuracy improvements are marginal.
This paper evaluates quantization techniques for deep learning inference.
problem Reducing the size and improving inference of deep neural networks.
method Review and empirical evaluation of quantization parameters for various neural network models.
result 8-bit quantization maintains accuracy within 1% of floating-point models.
Combining watermark and non-watermark detectors improves LLM detection.
problem Challenges in detecting watermarked language models due to limited entropy.
method Investigates hybrid schemes combining watermark and non-watermark detectors.
result Hybrid schemes outperform either class of detector under various conditions.
We calculate the Chern-Simons invariants of the twist knot orbifolds using the Schläfli formula for the generalized Chern-Simons function on the family of the twist knot cone-manifold structures. Following the general instruction of Hilden, Lozano, and Montesinos-Amilibia, we here present the concrete formulae and calc…
THERMOMETER calibrates LLMs efficiently for diverse tasks.
problem Calibrating large language models is challenging due to computational and versatility issues.
method THERMOMETER learns an auxiliary model for calibrating a LLM using data from multiple tasks.
result THERMOMETER produces better-calibrated responses for new tasks.
SAGE enhances reinforcement learning by injecting hints to prevent model stagnation.
problem Sparse rewards cause large language models to stall under relative policy optimization.
method SAGE injects privileged hints during training to increase within-group outcome diversity.
result SAGE consistently outperforms GRPO on 6 benchmarks with LLMs, achieving significant improvements.
Boolean tensor decomposition approximates data of multi-way binary relationships as product of interpretable low-rank binary factors, following the rules of Boolean algebra. Here, we present its first probabilistic treatment. We facilitate scalable sampling-based posterior inference by exploitation of the combinatorial…