More Like this

1. FinLoRA: Finetuning Quantized Financial Large Language Models Using Low-Rank Adaptation on GPUs

   Wang, D; Kim, D; Jin, B; Zhao, X; Fu, T; Yang, S Y; Liu, X (December 2024, arXiv preprints)

   Finetuned large language models (LLMs) have shown remarkable performance in financial tasks, such as sentiment analysis and information retrieval. Due to privacy concerns, finetuning and deploying financial LLMs (FinLLMs) locally are crucial for institutions and individuals. In this paper, we employ quantized low-rank adaptation (QLoRA) to finetune FinLLMs, which leverage low-rank structure and quantization technique to significantly reduce computational requirements while maintaining model performance. We also employ data and pipeline parallelism to enable local finetuning on commodity GPUs. Experiments on financial datasets validate the efficacy of our approach in yielding notable improvements over the base models. 

   more » « less
2. Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing

   Xu, Nan; Wang, Fei; Li, Bangzheng; Dong, Mingtao; Chen, Muhao (January 2022, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing)

   Entity typing aims at predicting one or more words that describe the type(s) of a specific mention in a sentence. Due to shortcuts from surface patterns to annotated entity labels and biased training, existing entity typing models are subject to the problem of spurious correlations. To comprehensively investigate the faithfulness and reliability of entity typing methods, we first systematically define distinct kinds of model biases that are reflected mainly from spurious correlations. Particularly, we identify six types of existing model biases, including mention-context bias, lexical overlapping bias, named entity bias, pronoun bias, dependency bias, and overgeneralization bias. To mitigate model biases, we then introduce a counterfactual data augmentation method. By augmenting the original training set with their debiasedcounterparts, models are forced to fully comprehend sentences and discover the fundamental cues for entity typing, rather than relying on spurious correlations for shortcuts. Experimental results on the UFET dataset show our counterfactual data augmentation approach helps improve generalization of different entity typing models with consistently better performance on both the original and debiased test sets. 

   more » « less
3. LEXPLAIN: Improving Model Explanations via Lexicon Supervision

   https://doi.org/10.18653/v1/2023.starsem-1.19  

   Ahia, Orevaoghene; Gonen, Hila; Balachandran, Vidhisha; Tsvetkov, Yulia; Smith, Noah (July 2023, Proceedings of the The 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023))

   Model explanations that shed light on the model’s predictions are becoming a desired additional output of NLP models, alongside their predictions. Challenges in creating these explanations include making them trustworthy and faithful to the model’s predictions. In this work, we propose a novel framework for guiding model explanations by supervising them explicitly. To this end, our method, LEXPLAIN, uses task-related lexicons to directly supervise model explanations. This approach consistently improves the plausibility of model’s explanations without sacrificing performance on the task, as we demonstrate on sentiment analysis and toxicity detection. Our analyses show that our method also demotes spurious correlations (i.e., with respect to African American English dialect) on toxicity detection, improving fairness. 

   more » « less
4. The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning

   Ye, Xi; Durrett, Greg (January 2022, Advances in neural information processing systems)

   Does prompting a large language model (LLM) like GPT-3 with explanations improve in-context learning? We study this question on two NLP tasks that involve reasoning over text, namely question answering and natural language inference. We test the performance of four LLMs on three textual reasoning datasets using prompts that include explanations in multiple different styles. For these tasks, we find that including explanations in the prompts for OPT, GPT-3 (davinci), and InstructGPT (text-davinci-001) only yields small to moderate accuracy improvements over standard few-show learning. However, text-davinci-002 is able to benefit more substantially. We further show that explanations generated by the LLMs may not entail the models' predictions nor be factually grounded in the input, even on simple tasks with extractive explanations. However, these flawed explanations can still be useful as a way to verify LLMs' predictions post-hoc. Through analysis in our three settings, we show that explanations judged by humans to be good---logically consistent with the input and the prediction---more likely cooccur with accurate predictions. Following these observations, we train calibrators using automatically extracted scores that assess the reliability of explanations, allowing us to improve performance post-hoc across all of our datasets. 

   more » « less
5. Language Models Don’t Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

   Turpin, M; Michael, J; Perez, E; Bowman, S R (February 2023, Advances in neural information processing systems)

   Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT explanations as the LLM’s process for solving a task. This level of transparency into LLMs’ predictions would yield significant safety benefits. However, we find that CoT explanations can systematically misrepresent the true reason for a model’s prediction. We demonstrate that CoT explanations can be heavily influenced by adding biasing features to model inputs—e.g., by reordering the multiple-choice options in a few-shot prompt to make the answer always “(A)”—which models systematically fail to mention in their explanations. When we bias models toward incorrect answers, they frequently generate CoT explanations rationalizing those answers. This causes accuracy to drop by as much as 36% on a suite of 13 tasks from BIG-Bench Hard, when testing with GPT-3.5 from OpenAI and Claude 1.0 from Anthropic. On a social-bias task, model explanations justify giving answers in line with stereotypes without mentioning the influence of these social biases. Our findings indicate that CoT explanations can be plausible yet misleading, which risks increasing our trust in LLMs without guaranteeing their safety. Building more transparent and explainable systems will require either improving CoT faithfulness through targeted efforts or abandoning CoT in favor of alternative methods. 

   more » « less