Language model benchmarks often misrepresent true understanding, revealing vulnerabilities in evaluation methods.
problem Language model benchmarks fail to accurately reflect true language understanding and adaptability.
method Systematic analysis of NLP evaluation frameworks, identifying vulnerabilities in static benchmarks, human evaluation protocols, and LLM-as-judge frameworks.
result Current evaluation methods are unreliable and need improvement to accurately assess LLM performance.
This paper uses LLMs and cycle consistency for better machine translation evaluation.
problem Evaluating translation quality and LLM capabilities without ground truth.
method Generate translation candidates, back-translate, and evaluate cycle consistency.
result Larger LLMs or more inference passes improve cycle consistency.
Paper introduces TrufLL for language model training without labeled data.
problem Training language models from scratch with reinforcement learning.
method Dynamic vocabulary truncation in RL for language generation.
result TrufLL successfully learns language generation policies from scratch.
FINCH dataset enables financial Text-to-SQL tasks, improving model evaluation.
problem Lack of a large-scale financial dataset for Text-to-SQL tasks.
method Curated financial dataset (FINCH), benchmarking reasoning and language models.
result Proposed FINCH Score for more accurate financial model evaluation.
Unlike major Western languages, most African languages are very low-resourced. Furthermore, the resources that do exist are often scattered and difficult to obtain and discover. As a result, the data and code for existing research has rarely been shared. This has lead a struggle to reproduce reported results, and few p…
A framework for optimizing prompt selection in generative language models.
problem Efficiently selecting prompts for generative language models.
method Two-stage framework using simulation optimization to maximize a pre-defined score.
result Consistency of the sequential evaluation procedure in the proposed framework.
Tiny benchmarks reduce LLM evaluation costs by using fewer examples.
problem Expensive evaluation of LLMs with tens of thousands of examples.
method Developed evaluation tools and tiny versions of popular benchmarks.
result Accurately estimate LLM performance with just 100 curated examples.
Active testing for large language models is made more efficient and accurate.
problem Efficient evaluation of large language models with limited labels.
method Cost-saving measures and in-context learning for constructing a surrogate model.
result Significantly more accurate evaluations of LLM performance compared to random data acquisition.
We conduct a large-scale, systematic study to evaluate the existing evaluation methods for natural language generation in the context of generating online product reviews. We compare human-based evaluators with a variety of automated evaluation procedures, including discriminative evaluators that measure how well machi…
Method guarantees coherent factuality for language model outputs in reasoning tasks.
problem Ensuring correctness of language model outputs in reasoning tasks.
method Developed a conformal-prediction-based method applied to subgraphs within a deducibility graph.
result Achieved coherent factuality across target coverage levels, 90% on stricter definition.
Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the translation of OOV words, specifically in those cases where OOV translations are der…
In this paper, we present Russian language datasets in the digital humanities domain for the evaluation of word embedding techniques or similar language modeling and feature learning algorithms. The datasets are split into two task types, word intrusion and word analogy, and contain 31362 task units in total. The chara…
Automates debiasing for large language model evaluations through Fisher random walk.
problem Rigorous and scalable evaluation of large language models.
method Semiparametric efficient estimator using Fisher random walk for weighted residual balancing.
result Efficient estimation of contextual preference scores for large language models.
A new framework evaluates large language models efficiently and accurately.
problem Evaluation of large language models is challenging due to stochasticity and heterogeneity of benchmarks.
method Interpretable and scalable framework based on Item Response Theory (IRT) and majorization-minimization principle.
result Our method achieves superior scalability and interpretability compared to existing approaches.
ALMANACS benchmarks explainability methods on simulatability.
problem Evaluating the effectiveness of explainability methods for language models.
method ALMANACS is a simulatability benchmark that evaluates explainability methods on twelve safety-relevant topics.
result No explainability method outperforms the explanation-free control across all topics.
StakeBench evaluates language understanding by linking comments to market commitments, improving model alignment with real-world outcomes.
problem Existing financial NLP benchmarks measure perceived language rather than market commitments.
method StakeBench uses observable market behavior to supervise models, testing their ability to detect commitments, identify sides, and project odds.
result Models partially recover position-side signals but struggle with later tasks, highlighting structural failures.
In this paper, we attempt to improve Statistical Machine Translation (SMT) systems on a very diverse set of language pairs (in both directions): Czech - English, Vietnamese - English, French - English and German - English. To accomplish this, we performed translation model training, created adaptations of training sett…
Text documents are structured on multiple levels of detail: individual words are related by syntax, but larger units of text are related by discourse structure. Existing language models generally fail to account for discourse structure, but it is crucial if we are to have language models that reward coherence and gener…
Study uses three sources to evaluate language models fairly.
problem Bias in offline model evaluation due to confounded model choice.
method Combines observational logs, randomized experiments, and simulators.
result Randomized experiment and simulator together recover causal model values.
This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers of self-attention that allow them to capture long range dependencies in sequential data. Dynamic evaluation fits models to the recent sequen…
Large language models correlate in errors, even with different architectures and providers.
problem Lack of empirical evidence on whether different large language models differ meaningfully.
method Empirical evaluation of over 350 large language models using two leaderboards and a resume-screening task.
result Large language models have substantial correlation in errors, even with distinct architectures and providers.
A new framework evaluates LLMs by considering judge reliability.
problem Evaluating LLMs without ground truth labels can lead to biased results.
method Introduces judge-specific discrimination parameters and estimates model quality and judge reliability.
result Improves agreement with human preferences and produces calibrated uncertainty quantification.
New method for evaluating LLMs reduces bias in open-ended evaluations.
problem Bias in Elo-based ratings of LLMs due to data redundancies.
method Proposes evaluation as a 3-player game and introduces novel solution concepts.
result Novel method leads to more robust and intuitive ratings.
ZeroSCROLLS benchmarks zero-shot natural language understanding over long texts.
problem Evaluate natural language understanding models over long texts without training data.
method Adapt six tasks from SCROLLS benchmark and add four new datasets, including novel aggregation tasks.
result Claude outperforms ChatGPT, and GPT-4 achieves highest average score.
The study uncovers latent capabilities of language models via causal representation learning.
problem Rigorous causal evaluations of language model capabilities are challenging due to confounding effects and computational costs.
method Proposes a causal representation learning framework to identify latent capability factors as causally interrelated after controlling for a common confounder (base model).
result Identifies a three-node linear causal structure explaining performance variations across 1500 models and six benchmarks.
Novel method diagnoses large language models' reasoning abilities.
problem Fine-grained evaluation of large language models' reasoning abilities.
method Adapting cognitive diagnosis models to LLMs, estimating mastery profiles and Q-matrix, incorporating textual information.
result Accurate parameter recovery and insights into LLMs' capabilities.
Bayesian approach quantifies uncertainty in LLM evaluations.
problem Statistical uncertainty in evaluating LLM behavior.
method Bayesian evaluation of LLM behavior using probabilistic text generation strategies.
result Bayesian approach provides useful uncertainty quantification about LLM behavior.
Shai is a 10B model for asset management tasks, outperforming baselines.
problem Improving performance in asset management tasks.
method Continuous pre-training and fine-tuning on asset management-specific data.
result Shai outperforms baseline models in asset management tasks.
Study evaluates five LLMs for financial report analysis, revealing performance differences and variability.
problem Lack of understanding in reliability, consistency, and transparency of LLMs in financial analysis.
method Human evaluation, automated similarity metrics, and behavioral diagnostics applied to five transformer-based LLMs over U.S. 10-K filings.
result No single LLM consistently dominates across all evaluation perspectives, highlighting variability and need for interpretability.
Transformer models improve arithmetic accuracy with number decomposition.
problem Transformer models struggle with arithmetic operations without decomposition.
method Fine-tuning models with a pipeline that decomposes numbers into units, tens, etc.
result Accuracy increased by 63% in five-digit addition tasks.
Many challenges in natural language processing require generating text, including language translation, dialogue generation, and speech recognition. For all of these problems, text generation becomes more difficult as the text becomes longer. Current language models often struggle to keep track of coherence for long pi…
Study evaluates LLMs like ChatGPT and GPT-4 on financial analysis tasks.
problem Assessing financial reasoning capabilities of large language models.
method Mock CFA exam questions, Zero-Shot, Chain-of-Thought, Few-Shot scenarios.
result LLMs perform well on financial analysis tasks, but have limitations.
Survey of financial LLMs in finance.
problem Limited research on Financial LLMs (FinLLMs).
method Chronological overview of PLMs, comparison of techniques, performance evaluations, and advanced tasks.
result Compilation of accessible datasets and benchmarks for AI research in finance.
Recent advances in multi-modal vision and language tasks enable a new set of applications. In this paper, we consider the task of generating natural language fashion feedback on outfit images. We collect a unique dataset, which contains outfit images and corresponding positive and constructive fashion feedback. We trea…
This research predicts stock market movements using Vision-Language models.
problem Predicting future stock market direction using historical data.
method Utilizing image and byte-based representations of stock data processed with Vision-Language models.
result The proposed approach significantly outperforms deep learning baselines.
Proposes a method to choose thresholds for LLM evaluation metrics.
problem Ensuring reliable large language models (LLMs) with correct threshold selection.
method Identify risks, stakeholders' risk tolerance, and use ground-truth data to determine thresholds.
result Demonstrates a concrete example with the Faithfulness metric and HaluBench dataset.
Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and languages. In this study, we propose a multilingual neural language model archite…
Improved language model for French clinical reports achieves state-of-the-art performance in medical NLP tasks.
problem Lack of specialized language models for French clinical reports.
method Adapted a general pre-trained language model (CamemBERT) to French clinical reports using a corpus of 21M reports.
result Pretrained and fine-tuned models improved F1-score by 3 percentage points on APMed task.
This research explores discrete diffusion models for natural language generation.
problem Challenges in applying diffusion models to discrete data, especially natural language.
method Investigates Discrete Denoising Diffusion Probabilistic Model (D3PM) and compares it with autoregressive models.
result Discrete diffusion models achieve better processing speed than autoregressive models.
Study constructs a Japanese financial LLM benchmark.
problem Need for domain-specific benchmarks for LLMs.
method Constructed a benchmark with multiple Japanese and financial domain tasks.
result GPT-4 outperforms other models in the benchmark.
Existing language models such as n-grams for software code often fail to capture a long context where dependent code elements scatter far apart. In this paper, we propose a novel approach to build a language model for software code to address this particular issue. Our language model, partly inspired by human memory, i…
Study evaluates if LLMs have company-specific biases in financial sentiment analysis.
problem Evaluating if large language models exhibit company-specific biases in financial sentiment analysis.
method Comparing sentiment scores with and without company names, constructing economic models, and empirical analysis.
result LLMs show company-specific biases in sentiment analysis, impacting investor behavior and stock prices.
Study evaluates LLMs for predicting Chinese stock movements using financial news sentiments.
problem Evaluating LLMs' ability to predict stock price movements using financial news sentiments.
method Standardized experimental procedure with three LLMs, each with unique performance enhancement methods.
result Developed quantitative trading strategies and conducted back-tests to assess LLMs' performance.
StableLM 2 1.6B is a new language model series with detailed evaluations and performance metrics.
problem Improving language models with smaller sizes and better performance.
method Detailed data and training procedure for StableLM 2 1.6B, including zero- and few-shot benchmarks and multilingual evaluations.
result StableLM 2 1.6B is the state-of-the-art open model under 2B parameters.
New method evaluates language model forecasters by checking consistency of predictions.
problem Evaluating the performance of language model forecasters is difficult due to lack of ground truth.
method Developed a consistency check framework based on arbitrage to evaluate forecasters.
result Consistency metrics correlate with ground truth performance of LLM forecasters.
Self-supervised skip-tree training improves mathematical reasoning in language models.
problem Improving logical reasoning in language models for formal mathematics.
method Self-supervised language modeling on mathematical formulas, skip-tree task.
result Models trained on skip-tree task outperform standard models in mathematical reasoning tasks.
In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation, specifically the use of encoder-decoder networks, to learn associations between natural language behavior descriptions and state-action informatio…
How can we measure whether a natural language generation system produces both high quality and diverse outputs? Human evaluation captures quality but not diversity, as it does not catch models that simply plagiarize from the training set. On the other hand, statistical evaluation (i.e., perplexity) captures diversity b…