Paper: arXiv 2502.16023

Abstract

We introduce the Contrastive Similarity Space Embedding Algorithm (ContraSim), a novel framework for uncovering the global semantic relationships between daily financial headlines and market movements. ContraSim operates in two key stages: (I) Weighted Headline Augmentation, which generates augmented financial headlines along with a semantic fine-grained similarity score, and (II) Weighted Self-Supervised Contrastive Learning (WSSCL), an extended version of classical self-supervised contrastive learning that uses the similarity metric to create a refined weighted embedding space. This embedding space clusters semantically similar headlines together, facilitating deeper market insights. Empirical results demonstrate that integrating ContraSim features into financial forecasting tasks improves classification accuracy from WSJ headlines by 7%. Moreover, leveraging an information density analysis, we find that the similarity spaces constructed by ContraSim intrinsically cluster days with homogeneous market movement directions, indicating that ContraSim captures market dynamics independent of ground truth labels. Additionally, ContraSim enables the identification of historical news days that closely resemble the headlines of the current day, providing analysts with actionable insights to predict market trends by referencing analogous past events.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper employs advanced machine learning concepts like contrastive learning and LLMs, but the mathematical presentation is mostly descriptive and lacks deep derivations or formal proofs. Empirically, it reports specific quantitative results (7% accuracy improvement) and describes a concrete pipeline using WSJ headlines, suggesting a backtest-ready approach.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Uncover semantic relationships<br>between financial headlines<br>and market movements"] --> B["Input Data<br>WSJ Headlines + Market Data"]
  B --> C["Stage I: Weighted Headline Augmentation<br>Generates augmented headlines<br>with fine-grained similarity scores"]
  C --> D["Stage II: WSSCL<br>Weighted Self-Supervised Contrastive Learning<br>Creates refined embedding space"]
  D --> E["Key Finding 1: 7% Accuracy Boost<br>ContraSim features improve<br>market classification accuracy"]
  D --> F["Key Finding 2: Intrinsic Clustering<br>Similarity spaces cluster days<br>by homogeneous market movements"]
  D --> G["Key Finding 3: Actionable Insights<br>Identifies historical analogs for<br>current headlines to predict trends"]

Cited References (338)

  1. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction (2018) — link
  2. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2020) — link
  3. A survey of inverse reinforcement learning (2022)
  4. Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation (1982) — link
  5. Asynchronous methods for deep reinforcement learning (2016)
  6. Learning Task Automata for Reinforcement Learning using Hidden Markov Models (2022) — link
  7. Apprenticeship learning via inverse reinforcement learning (2004)
  8. Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation (2017)
and 330 more
  1. Spam Detection using Machine Learning and Deep Learning Techniques (2022)
  2. How to Leverage a Multi-layered Transformer Language Model for Text Clustering: an Ensemble Approach (2021) — link
  3. A hybrid learning approach to detecting regime switches in financial markets (2020)
  4. ImageNet Classification with Deep Convolutional Neural Networks (2012) — link
  5. A general class of coefficients of divergence of one distribution from another (1966)
  6. Stanford Alpaca: An Instruction-following LLaMA model (2023)
  7. Alpaca: A strong, replicable instruction-following model (2023)
  8. Self-instruct: Aligning language model with self generated instructions (2022) — link
  9. Highly accurate protein structure prediction with AlphaFold (2021) — link
  10. Solving olympiad geometry without human demonstrations (2024)
  11. Mastering the game of Go with deep neural networks and tree search (2016) — link
  12. Grandmaster level in StarCraft II using multi-agent reinforcement learning (2019)
  13. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017) — link
  14. Domain adaption of named entity recognition to support credit risk assessment (2015)
  15. Mean-variance investing (2012)
  16. Connected stocks (2014)
  17. Is all that talk just noise? The information content of internet stock message boards (2004)
  18. Finbert: Financial sentiment analysis with pre-trained language models (2019) — link
  19. A survey of robot learning from demonstration (2009)
  20. A survey of inverse reinforcement learning: Challenges, methods and progress (2021)
  21. An application of inverse reinforcement learning to medical records of diabetes treatment (2013)
  22. Bayesian portfolio analysis (2010)
  23. Scalable bayesian inverse reinforcement learning (2021) — link
  24. Action understanding as inverse planning (2009)
  25. BELLE: Be Everyone’s Large Language model Engine (2023)
  26. Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases (2023) — link
  27. Training verifiers to solve math word problems (2021) — link
  28. Evaluating large language models trained on code (2021) — link
  29. Scaling Learning Algorithms Towards AI (2007)
  30. Reinforcement learning and optimal control (2019)
  31. Explainable Artificial Intelligence (XAI) in Credit Risk Management (2019) — link
  32. Multimodal datasets: misogyny, pornography, and malignant stereotypes (2021)
  33. Probabilistic topic models (2012)
  34. Twitter mood predicts the stock market (2011)
  35. Generalized autoregressive conditional heteroskedasticity (1986)
  36. On the opportunities and risks of foundation models (2021)
  37. Time Series Analysis: Forecasting and Control (1970)
  38. An introduction to evolutionary computation in finance (2008)
  39. OpenAI gym (2016) — link
  40. Investor sentiment and the near-term stock market (2004)
  41. Language Models are Few-Shot Learners (2020) — link
  42. Language models are few-shot learners (2020)
  43. Sparks of artificial general intelligence: Early experiments with GPT-4 (2023)
  44. Fairness and Abstraction in Sociotechnical Systems (2016)
  45. Jumping NLP curves: A review of natural language processing research (2014)
  46. Affective computing and sentiment analysis (2017)
  47. Density-based clustering based on hierarchical density estimates (2013)
  48. Multi-modal deep learning system for forecasting the evolution of financial time series (2021)
  49. Computational intelligence and financial markets: A survey and future directions (2016)
  50. Learning by cheating (2020)
  51. A simple framework for contrastive learning of visual representations (2020)
  52. Exploring simple siamese representation learning (2021)
  53. FinQA: A Dataset of Numerical Reasoning over Financial Data (2021)
  54. Convfinqa: Exploring the chain of numerical reasoning in conversational finance question answering (2022) — link
  55. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017) — link
  56. Inverse reinforcement learning in partially observable environments
  57. Inverse reinforcement learning in partially observable environments (2011)
  58. PaLM : Scaling language modeling with pathways. 2022 (2022)
  59. Electra: Pre-training text encoders as discriminators rather than generators (2020) — link
  60. Training verifiers to solve math word problems (2021) — link
  61. Code llama: Open foundation models for code (2023) — link
  62. Good debt or bad debt: Detecting semantic orientations in economic texts (2014)
  63. Introducing DBRX: A New State-of-the-Art Open LLM (2024)
  64. Continuous control with deep reinforcement learning (2015) — link
  65. Advances in financial machine learning (2018)
  66. LLM-Informed Multi-Armed Bandit Strategies for Non-Stationary Environments (2023) — link
  67. BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding (2019) — link
  68. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2019)
  69. Deep Learning for Event-Driven Stock Prediction (2015)
  70. Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus (2021) — link
  71. Direct preference optimization: Your language model is secretly a reward model (2023) — link
  72. GLaM: Efficient Scaling of Language Models with Mixture-of-Experts (2022)
  73. An empirical investigation of the challenges of real-world reinforcement learning (2020)
  74. Co-integration and error correction: representation, estimation, and testing (1987)
  75. Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions (2022) — link
  76. Towards Explainable AI for Autonomous Driving Using Paired Sample Comparisons (2018)
  77. A framework for few-shot language model evaluation (2021) — link
  78. Bartscore: Evaluating generated text as text generation (2021)
  79. Bertscore: Evaluating text generation with bert (2019) — link
  80. Stochastic processes and filtering theory (2007)
  81. f-irl: Inverse reinforcement learning via state marginal matching (2020) — link
  82. Billion-scale similarity search with GPUs (2019)
  83. Efficient capital markets: A review of theory and empirical work (1970)
  84. Efficient capital markets: reply (1976)
  85. Efficient capital markets: II (1991)
  86. Market efficiency, long-term returns, and behavioral finance (1998)
  87. Stock movement prediction from tweets and historical prices (2018)
  88. Accurate Stock Movement Prediction with Self-supervised Learning from Sparse Noisy Tweets (2022)
  89. Hybrid deep sequential modeling for social text-driven stock prediction (2018)
  90. Www'18 open challenge: financial opinion mining and question answering (2018)
  91. SENTiVENT: enabling supervised information extraction of company-specific events in economic and financial news (2022)
  92. Good debt or bad debt: Detecting semantic orientations in economic texts (2014)
  93. NIFTY Financial News Headlines Dataset (2024) — link
  94. Is domain adaptation worth your investment? Comparing BERT and FinBERT on financial tasks (2021)
  95. Finbert: Financial sentiment analysis with pre-trained language models (2019) — link
  96. PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance (2023) — link
  97. Guided cost learning: Deep inverse optimal control via policy optimization (2016)
  98. Stock Market Prediction Using Deep Learning Models (2018)
  99. Quadratic optimization (1995)
  100. Profitable momentum trading strategies for individual investors (2015)
  101. Interpretable Explanations of Black Boxes by Meaningful Perturbation (2017)
  102. Learning robust rewards with adversarial inverse reinforcement learning (2017) — link
  103. Generative adversarial imitation learning (2016) — link
  104. Automata-theoretic approach to planning for temporally extended goals (1999)
  105. Tabu search (1998)
  106. Explainable AI for Robot Failures: Generating Explanations that Improve User Understanding (2018)
  107. Deep learning (2016)
  108. GPT-NeoX-20B : An Open-Source Autoregressive Language Model (2022) — link
  109. Language Models are Few-Shot Learners (2020)
  110. The Future of Financial Analysis (1963)
  111. GraphCast: Learning skillful medium-range global weather forecasting (2022) — link
  112. Learning Word Vectors for 157 Languages (2018)
  113. Can we trust Bayesian uncertainty quantification from Gaussian process priors with squared exponential covariance kernel? (2021)
  114. Inverse reinforcement learning using expectation maximization in mixture models (2015)
  115. A new approach to the economic analysis of nonstationary time series and the business cycle (1989)
  116. Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning — → 2301.10724
  117. Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning (2023)
  118. Parrondo’s paradox (1999)
  119. The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2009)
  120. Momentum contrast for unsupervised visual representation learning (2020)
  121. BPE mb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages (2018)
  122. Studies in the Logic of Explanation (1948)
  123. OptionGAN : Learning joint reward-policy options using generative adversarial inverse reinforcement learning (2018)
  124. Measuring Massive Multitask Language Understanding (2021)
  125. A Fast Learning Algorithm for Deep Belief Nets (2006)
  126. Forecasting seasonals and trends by exponentially weighted averages (1957)
  127. A Deep Learning Approach for Stock Market Prediction Based on Financial News (2018)
  128. Transformers Documentation (2024)
  129. Imitation learning: A survey of learning methods (2017)
  130. Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning (2020) — link
  131. Reward machines: Exploiting reward function structure in reinforcement learning (2022)
  132. Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks (2023)
  133. Information theory and statistical mechanics. II (1957)
  134. A deep reinforcement learning framework for the financial portfolio management problem (2017) — link
  135. Financial Trading as a Game: A Deep Reinforcement Learning Approach (2017)
  136. Scaling Sentence Embeddings with Large Language Models (2023) — link
  137. Mixtral of Experts (2024) — link
  138. A Statistical Interpretation of Term Specificity and Its Application in Retrieval (1972)
  139. Challenges and Applications of Large Language Models (2023) — link
  140. Planning and acting in partially observable stochastic domains (1998)
  141. A natural policy gradient (2001)
  142. Deep kalman filters (2015) — link
  143. Understanding the Kalman filter (1983)
  144. A new approach to linear filtering and prediction problems (1960)
  145. Asymptotics of maximum likelihood parameter estimates for gaussian processes: The ornstein–uhlenbeck prior (2019)
  146. Champion-level drone racing using deep reinforcement learning (2023)
  147. Evaluating Sentiment Analysis in the Context of Securities Trading. (2016)
  148. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2019)
  149. Unnatural language processing (2023) — link
  150. Supervised Contrastive Learning (2021) — link
  151. Portfolio Transformer for Attention-Based Asset Allocation (2022) — link
  152. Learning Goal Conditioned Socially Compliant Navigation From Demonstration Using Risk-Based Features (2021)
  153. Decision support from financial disclosures with deep neural networks and transfer learning (2017)
  154. Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets (2022) — link
  155. Sentiment analysis of financial news articles using performance indicators (2018)
  156. Reinforcement Learning for Optimizing RAG for Domain Chatbots (2024) — link
  157. Deduplicating Training Data Makes Language Models Better (2022) — link
  158. Rcv1: A new benchmark collection for text categorization research (2004)
  159. BART : Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension (2020) — link
  160. Solving quantitative reasoning problems with language models (2022) — link
  161. Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? An Examination on Several Typical Tasks (2023) — link
  162. TradingGPT: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance (2023) — link
  163. Holistic evaluation of language models (2022)
  164. Reinforcement learning for robots using neural networks (1992)
  165. Predictive representations of state (2001)
  166. RoBERTa: A Robustly Optimized BERT Pretraining Approach (2019) — link
  167. Adaptive quantitative trading: An imitative deep reinforcement learning approach (2020)
  168. Financial News Prediction Using Pre-Trained Language Models (2021)
  169. FinRL-Meta: Market environments and benchmarks for data-driven financial reinforcement learning (2022)
  170. LLaMA : Open and efficient foundation language models (2023)
  171. Llama 2: Open foundation and fine-tuned chat models (2023) — link
  172. The flan collection: Designing data and methods for effective instruction tuning (2023) — link
  173. Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models — → 2304.07619
  174. Decoupled weight decay regularization (2017) — link
  175. Textual analysis in accounting and finance: A survey (2016)
  176. Learning Reward Machines for Partially Observable Reinforcement Learning (2019) — link
  177. BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark (2023) — link
  178. Individual choice behavior: A theoretical analysis (2005)
  179. Visualizing data using t-SNE (2008)
  180. Data Contamination: From Memorization to Exploitation (2022) — link
  181. Www'18 open challenge: financial opinion mining and question answering (2018)
  182. A random walk down wall street [by] burton G. Malkiel (1973)
  183. Efficient market hypothesis (1989)
  184. Passive investment strategies and efficient markets (2003)
  185. Good debt or bad debt: Detecting semantic orientations in economic texts (2014)
  186. Analysis of time series subject to changes in regime (1990)
  187. A new approach to the economic analysis of nonstationary time series and the business cycle (1989)
  188. Foundations of portfolio theory (1991)
  189. Maximum Entropy Inverse Reinforcement Learning. (2008) — link
  190. UMAP: Uniform manifold approximation and projection for dimension reduction (2018) — link
  191. Maximum Entropy Deep Inverse Reinforcement Learning (2016) — link
  192. Introducing Meta Llama 3: The Most Capable Openly Available LLM to Date (2024)
  193. Solving POMDPs by searching the space of finite policies (2013) — link
  194. Mistral 7B (2023) — link
  195. Asynchronous methods for deep reinforcement learning (2016)
  196. CLUES: few-shot learning evaluation in natural language understanding (2021)
  197. Algorithms for inverse reinforcement learning. (2000)
  198. Reuters Dataset at TREC (2024)
  199. Representation learning with contrastive predictive coding (2018) — link
  200. OpenAI gym (2016) — link
  201. GPT-4 Technical Report (2023) — link
  202. GPT-4 Technical Report (2023)
  203. OpenAI API (2024)
  204. OpenAI Baselines (2017)
  205. Training language models to follow instructions with human feedback (2022)
  206. What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning (2023) — link
  207. LIII. On lines and planes of closest fit to systems of points in space (1901)
  208. Parameter-efficient transfer learning for NLP (2019)
  209. Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale (2022)
  210. Lora: Low-rank adaptation of large language models (2021) — link
  211. Prefix-tuning: Optimizing continuous prompts for generation (2021) — link
  212. Qlora: Efficient finetuning of quantized llms (2023) — link
  213. Variational discriminator bottleneck: Improving imitation learning, inverse rl, and gans by constraining information flow (2018) — link
  214. Deep Contextualized Word Representations (2018) — link
  215. The analysis of permutations (1975)
  216. Proximal policy optimization algorithms (2017) — link
  217. Proximal policy optimization algorithms (2017) — link
  218. Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning (2018) — link
  219. Language Models are Unsupervised Multitask Learners (2019)
  220. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2020)
  221. Retrieval-augmented generation for large language models: A survey (2023) — link
  222. Dynamic asset allocation for varied financial markets under regime switching framework (2014)
  223. Regime changes and financial markets (2012)
  224. Size and value anomalies under regime shifts (2008)
  225. Markov switching models in empirical finance (2011)
  226. Regime switching models (2010)
  227. Clustering market regimes using the wasserstein distance (2021) — link
  228. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (2019) — link
  229. Highly accurate protein structure prediction with AlphaFold (2021) — link
  230. Reinforcement learning in financial markets - a survey (2018)
  231. Training a helpful and harmless assistant with reinforcement learning from human feedback (2022) — link
  232. A general language assistant as a laboratory for alignment (2021) — link
  233. Training language models to follow instructions with human feedback, 2022 (2022)
  234. Learning to summarize with human feedback (2020)
  235. Fine-tuning language models from human preferences (2019) — link
  236. Adapting rapid motor adaptation for bipedal robots (2022)
  237. Learning quadrupedal locomotion over challenging terrain (2020)
  238. Learning to walk via deep reinforcement learning (2018) — link
  239. Learning agile and dynamic motor skills for legged robots (2019)
  240. Learning locomotion skills for cassie: Iterative design and sim-to-real (2020)
  241. Learning robust perceptive locomotion for quadrupedal robots in the wild (2022)
  242. Advances in real-world applications for legged robots (2018)
  243. Probabilistic terrain mapping for mobile robots with uncertain localization (2018)
  244. Learning agile robotic locomotion skills by imitating animals (2020) — link
  245. Development of quadruped walking robots: A review (2021)
  246. Learning agents for uncertain environments (1998)
  247. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor (2018)
  248. Multitask Prompted Training Enables Zero-Shot Task Generalization (2022)
  249. PrivySense: Price Volatility based Sentiment Estimation from Financial News using Machine Learning (2017) — link
  250. NIFTY Financial News Headlines Dataset (2024) — link
  251. What Teaches Robots to Walk, Teaches Them to Trade too – Regime Adaptive Execution using Informed Data and LLMs (2024) — link
  252. Bloom: A 176b-parameter open-access multilingual language model (2022) — link
  253. Gradient estimation using stochastic computation graphs (2015)
  254. High-dimensional continuous control using generalized advantage estimation (2015) — link
  255. Optimizing expectations: From deep reinforcement learning to stochastic computation graphs (2016)
  256. An analysis of verbs in financial news articles and their impact on stock price (2010)
  257. Tensor-Based Learning for Predicting Stock Movements (2018)
  258. WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain (2022) — link
  259. A Mathematical Theory of Communication (1948)
  260. ShareGPT (2024)
  261. The Sharpe Ratio (1994)
  262. The 37 Implementation Details of Proximal Policy Optimization (2022) — link
  263. Megatron-lm: Training multi-billion parameter language models using model parallelism (2019)
  264. Sim-to-real transfer of robotic control with dynamics randomization (2018)
  265. Learning agile and dynamic motor skills for legged robots (2019)
  266. Sim-to-real: Learning agile locomotion for quadruped robots (2018) — link
  267. Domain randomization for transferring deep neural networks from simulation to the real world (2017)
  268. Macroeconomics and reality (1980)
  269. Analyzing Transformer Dynamics as Movement through Embedding Space (2023) — link
  270. Impact of news on the commodity market: Dataset and results (2021)
  271. MPNet: Masked and Permuted Pre-training for Language Understanding (2020)
  272. GlobalBench : A Benchmark for Global Progress in Natural Language Processing (2023)
  273. Accurate Stock Movement Prediction with Self-supervised Learning from Sparse Noisy Tweets (2022)
  274. CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss (2023) — link
  275. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models (2022)
  276. Stable-baselines3: Reliable reinforcement learning implementations (2021)
  277. Stock Market Prediction Using Deep Reinforcement Learning (2023) — link
  278. Nonparametric belief propagation (2010)
  279. Policy gradient methods for reinforcement learning with function approximation (1999)
  280. Reinforcement learning: An introduction (2018)
  281. True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning (2024) — link
  282. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling (2018) — link
  283. Addressing function approximation error in actor-critic methods (2018)
  284. TF–IDF (2010) — link
  285. Mujoco: A physics engine for model-based control (2012)
  286. Llama: Open and efficient foundation language models (2023) — link
  287. Trust Region Policy Optimization (2015) — link
  288. Forecasting stock returns with ensemble learning and sentiment analysis (2016)
  289. On the theory of the Brownian motion (1930)
  290. Visualizing data using t-SNE. (2008)
  291. An automata-theoretic approach to linear temporal logic (1996)
  292. Attention is all you need (2017)
  293. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality (2023) — link
  294. Efficient Memory Management for Large Language Model Serving with PagedAttention (2023)
  295. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding (2019)
  296. SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems (2019)
  297. Self-Instruct: Aligning Language Model with Self Generated Instructions (2022) — link
  298. Text Embeddings by Weakly-Supervised Contrastive Pre-training (2022)
  299. Learning Belief Representations for Partially Observable Deep RL (2023)
  300. Self-Instruct: Aligning Language Models with Self-Generated Instructions (2023) — link
  301. Finetuned language models are zero-shot learners (2021) — link
  302. Finetuned Language Models are Zero-Shot Learners (2022)
  303. Chain-of-thought prompting elicits reasoning in large language models (2022)
  304. Emergent abilities of large language models (2022)
  305. Weighted contrastive learning using pseudo labels for facial expression recognition (2022) — link
  306. Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext (2017) — link
  307. Slow feature analysis: Unsupervised learning of invariances (2002)
  308. The Wall Street Journal (2024)
  309. Bloomberggpt: A large language model for finance (2023) — link
  310. Maximum entropy deep inverse reinforcement learning (2015) — link
  311. The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT Over MultiModal Stock Movement Prediction Challenges — → 2304.05351
  312. Natural language based financial forecasting: a survey (2018)
  313. Temporal Data Meets LLM – Explainable Financial Time Series Forecasting (2023) — link
  314. Sentiment Analysis for Stock Price Prediction Using Deep Learning Models (2018)
  315. Stock movement prediction from tweets and historical prices (2018)
  316. XLNet: Generalized Autoregressive Pretraining for Language Understanding (2019)
  317. Finbert: A pretrained language model for financial communications (2020) — link
  318. ConES: Concept Embedding Search for Parameter Efficient Tuning Large Vision Language Models (2023) — link
  319. Teacher Guided Training: An Efficient Framework for Knowledge Transfer (2022) — link
  320. Zephyr: Direct distillation of lm alignment (2023) — link
  321. Mengzi: Towards lightweight yet ingenious pre-trained models for chinese (2021) — link
  322. Multi-Modal Financial Forecasting Using Contrastive Learning (2021)
  323. Opt: Open pre-trained transformer language models (2022) — link
  324. Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements? (2023) — link
  325. A survey of large language models (2023)
  326. FaceNet: A Unified Embedding for Face Recognition and Clustering (2015)
  327. Learning Word Vectors for Sentiment Analysis (2011) — link
  328. Geometric k-nearest neighbor estimation of entropy and mutual information (2018) — link
  329. Notes on Kullback-Leibler Divergence and Likelihood (2014) — link
  330. Divergence measures based on the Shannon entropy (1991) — link

3 of 338 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.