Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a key limitation remains: LMs, primarily optimized for natural language understanding and generation, struggle with multi-step reasoning, planning, and using environmental feedback when attempting to solve realistic computer tasks. Towards addressing this, we propose an inference-time search algorithm for LM agents to explicitly perform exploration and multi-step planning in interactive web environments. Our approach is a form of best-first tree search that operates within the actual environment space, and is complementary with most existing state-of-the-art agents. It is the first tree search algorithm for LM agents that shows effectiveness on realistic web tasks. On the challenging VisualWebArena benchmark, applying our search algorithm on top of a GPT-4o agent yields a 39.7% relative increase in success rate compared to the same baseline without search, setting a state-of-the-art success rate of 26.4%. On WebArena, search also yields a 28.0% relative improvement over a baseline agent, setting a competitive success rate of 19.2%. Our experiments highlight the effectiveness of search for web agents, and we demonstrate that performance scales with increased test-time compute. We conduct a thorough analysis of our results to highlight improvements from search, limitations, and promising directions for future work. Our code and models are publicly released at https://jykoh.com/search-agents.
In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and solving mathematical problems, leading to advancements in various fields. We propose an LLM-embodied path planning framework for mobile agents, focusing on solving high-level coverage path planning issues and low-level control. Our proposed multi-layer architecture uses prompted LLMs in the path planning phase and integrates them with the mobile agents' low-level actuators. To evaluate the performance of various LLMs, we propose a coverage-weighted path planning metric to assess the performance of the embodied models. Our experiments show that the proposed framework improves LLMs' spatial inference abilities. We demonstrate that the proposed multi-layer framework significantly enhances the efficiency and accuracy of these tasks by leveraging the natural language understanding and generative capabilities of LLMs. Our experiments show that this framework can improve LLMs' 2D plane reasoning abilities and complete coverage path planning tasks. We also tested three LLM kernels: gpt-4o, gemini-1.5-flash, and claude-3.5-sonnet. The experimental results show that claude-3.5 can complete the coverage planning task in different scenarios, and its indicators are better than those of the other models.
Large language models (LLMs) have significantly advanced natural language understanding and demonstrated strong problem-solving abilities. Despite these successes, most LLMs still struggle with solving mathematical problems due to the intricate reasoning required. This paper investigates the mathematical problem-solving capabilities of LLMs using the newly developed "MathOdyssey" dataset. The dataset includes diverse mathematical problems at high school and university levels, created by experts from notable institutions to rigorously test LLMs in advanced problem-solving scenarios and cover a wider range of subject areas. By providing the MathOdyssey dataset as a resource to the AI community, we aim to contribute to the understanding and improvement of AI capabilities in complex mathematical problem-solving. We conduct benchmarking on open-source models, such as Llama-3 and DBRX-Instruct, and closed-source models from the GPT series and Gemini models. Our results indicate that while LLMs perform well on routine and moderately difficult tasks, they face significant challenges with Olympiad-level problems and complex university-level questions. Our analysis shows a narrowing performance gap between open-source and closed-source models, yet substantial challenges remain, particularly with the most demanding problems. This study highlights the ongoing need for research to enhance the mathematical reasoning of LLMs. The dataset, results, and code are publicly available.
Large language models (LLMs) have shown substantial progress in natural language understanding and generation, proving valuable especially in the medical field. Despite advancements, challenges persist due to the complexity and diversity inherent in medical tasks, which can be categorized as knowledge-intensive tasks and alignment-required tasks. Previous approaches either ignore the latter task or focus on a minority of tasks and hence lose generalization. To address these drawbacks, we propose a progressive fine-tuning pipeline. This pipeline employs a Knowledge Aggregator and a Noise aggregator to encode diverse knowledge in the first stage and filter out detrimental information. In the second stage, we drop the Noise Aggregator to avoid the interference of suboptimal representation and leverage an additional alignment module optimized towards an orthogonal direction to the knowledge space to mitigate knowledge forgetting. Based on this two-stage paradigm, we proposed a Medical LLM through decoupling Clinical Alignment and Knowledge Aggregation (MedCare), which is designed to achieve state-of-the-art (SOTA) performance on over 20 medical tasks, as well as SOTA results on specific medical alignment tasks. Various model sizes of MedCare (1.8B, 7B, 14B) all demonstrate significant improvements over existing models with similar model sizes.
The development of Natural Language Processing (NLI) datasets and models has been inspired by innovations in annotation design. With the rapid development of machine learning models today, the performance of existing machine learning models has quickly reached state-of-the-art results on a variety of tasks related to natural language processing, including natural language inference tasks. By using a pre-trained model during the annotation process, it is possible to challenge current NLI models by having humans produce premise-hypothesis combinations that the machine model cannot correctly predict. To remain attractive and challenging in the research of natural language inference for Vietnamese, in this paper, we introduce the adversarial NLI dataset to the NLP research community with the name ViANLI. This data set contains more than 10K premise-hypothesis pairs and is built by a continuously adjusting process to obtain the most out of the patterns generated by the annotators. ViANLI dataset has brought many difficulties to many current SOTA models when the accuracy of the most powerful model on the test set only reached 48.4%. Additionally, the experimental results show that the models trained on our dataset have significantly improved the results on other Vietnamese NLI datasets.
As Large Language Models (LLMs) continue to exhibit remarkable performance in natural language understanding tasks, there is a crucial need to measure their ability for human-like multi-step logical reasoning. Existing logical reasoning evaluation benchmarks often focus primarily on simplistic single-step or multi-step reasoning with a limited set of inference rules. Furthermore, the lack of datasets for evaluating non-monotonic reasoning represents a crucial gap since it aligns more closely with human-like reasoning. To address these limitations, we propose Multi-LogiEval, a comprehensive evaluation dataset encompassing multi-step logical reasoning with various inference rules and depths. Multi-LogiEval covers three logic types--propositional, first-order, and non-monotonic--consisting of more than 30 inference rules and more than 60 of their combinations with various depths. Leveraging this dataset, we conduct evaluations on a range of LLMs including GPT-4, ChatGPT, Gemini-Pro, Yi, Orca, and Mistral, employing a zero-shot chain-of-thought. Experimental results show that there is a significant drop in the performance of LLMs as the reasoning steps/depth increases (average accuracy of ~68% at depth-1 to ~43% at depth-5). We further conduct a thorough investigation of reasoning chains generated by LLMs which reveals several important findings. We believe that Multi-LogiEval facilitates future research for evaluating and enhancing the logical reasoning ability of LLMs. Data is available at https://github.com/Mihir3009/Multi-LogiEval.
We propose MMLU-SR, a novel dataset designed to measure the true comprehension abilities of Large Language Models (LLMs) by challenging their performance in question-answering tasks with modified terms. We reasoned that an agent that "truly" understands a concept can still evaluate it when key terms are replaced by suitably defined alternate terms, and sought to differentiate such comprehension from mere text replacement. In our study, we modified standardized test questions by replacing a key term with a dummy word along with its definition. The key term could be in the context of questions, answers, or both questions and answers. Notwithstanding the high scores achieved by recent popular LLMs on the MMLU leaderboard, we found a substantial reduction in model performance after such replacement, suggesting poor comprehension. This new benchmark provides a rigorous benchmark for testing true model comprehension, and poses a challenge to the broader scientific community.
Knowledge-enhanced pre-trained language models (KEPLMs) leverage relation triples from knowledge graphs (KGs) and integrate these external data sources into language models via self-supervised learning. Previous works treat knowledge enhancement as two independent operations, i.e., knowledge injection and knowledge integration. In this paper, we propose to learn Knowledge-Enhanced language representations with Hierarchical Reinforcement Learning (KEHRL), which jointly addresses the problems of detecting positions for knowledge injection and integrating external knowledge into the model in order to avoid injecting inaccurate or irrelevant knowledge. Specifically, a high-level reinforcement learning (RL) agent utilizes both internal and prior knowledge to iteratively detect essential positions in texts for knowledge injection, which filters out less meaningful entities to avoid diverting the knowledge learning direction. Once the entity positions are selected, a relevant triple filtration module is triggered to perform low-level RL to dynamically refine the triples associated with polysemic entities through binary-valued actions. Experiments validate KEHRL's effectiveness in probing factual knowledge and enhancing the model's performance on various natural language understanding tasks.
Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data generated by token surface matching, regardless of the global context-aware semantics of the surrounding text tokens. In this paper, we propose an Unsupervised Pseudo Semantic Data Augmentation (UniPSDA) mechanism for cross-lingual natural language understanding to enrich the training data without human interventions. Specifically, to retrieve the tokens with similar meanings for the semantic data augmentation across different languages, we propose a sequential clustering process in 3 stages: within a single language, across multiple languages of a language family, and across languages from multiple language families. Meanwhile, considering the multi-lingual knowledge infusion with context-aware semantics while alleviating computation burden, we directly replace the key constituents of the sentences with the above-learned multi-lingual family knowledge, viewed as pseudo-semantic. The infusion process is further optimized via three de-biasing techniques without introducing any neural parameters. Extensive experiments demonstrate that our model consistently improves the performance on general zero-shot cross-lingual natural language understanding tasks, including sequence classification, information extraction, and question answering.
This paper explores the performance of encoder and decoder language models on multilingual Natural Language Understanding (NLU) tasks, with a broad focus on Germanic languages. Building upon the ScandEval benchmark, initially restricted to evaluating encoder models, we extend the evaluation framework to include decoder models. We introduce a method for evaluating decoder models on NLU tasks and apply it to the languages Danish, Swedish, Norwegian, Icelandic, Faroese, German, Dutch, and English. Through a series of experiments and analyses, we also address research questions regarding the comparative performance of encoder and decoder models, the impact of NLU task types, and the variation across language resources. Our findings reveal that encoder models can achieve significantly better NLU performance than decoder models despite having orders of magnitude fewer parameters. Additionally, we investigate the correlation between decoders and task performance via a UMAP analysis, shedding light on the unique capabilities of decoder and encoder models. This study contributes to a deeper understanding of language model paradigms in NLU tasks and provides valuable insights for model selection and evaluation in multilingual settings.
Recently, large language models (LLMs) have been widely researched in the field of graph machine learning due to their outstanding abilities in language comprehension and learning. However, the significant gap between natural language tasks and topological structure modeling poses a nonnegligible challenge. Specifically, since natural language descriptions are not sufficient for LLMs to understand and process graph-structured data, fine-tuned LLMs perform even worse than some traditional GNN models on graph tasks, lacking inherent modeling capabilities for graph structures. Existing research overly emphasizes LLMs' understanding of semantic information captured by external models, while inadequately exploring graph topological structure modeling, thereby overlooking the genuine capabilities that LLMs lack. Consequently, in this paper, we introduce a new framework, LangTopo, which aligns graph structure modeling with natural language understanding at the token level. LangTopo quantifies the graph structure modeling capabilities of GNNs and LLMs by constructing a codebook for the graph modality and performs consistency maximization. This process aligns the text description of LLM with the topological modeling of GNN, allowing LLM to learn the ability of GNN to capture graph structures, enabling LLM to handle graph-structured data independently. We demonstrate the effectiveness of our proposed method on multiple datasets.
Despite their vast capabilities, Large Language Models (LLMs) often struggle with generating reliable outputs, frequently producing high-confidence inaccuracies known as hallucinations. Addressing this challenge, our research introduces InternalInspector, a novel framework designed to enhance confidence estimation in LLMs by leveraging contrastive learning on internal states including attention states, feed-forward states, and activation states of all layers. Unlike existing methods that primarily focus on the final activation state, InternalInspector conducts a comprehensive analysis across all internal states of every layer to accurately identify both correct and incorrect prediction processes. By benchmarking InternalInspector against existing confidence estimation methods across various natural language understanding and generation tasks, including factual question answering, commonsense reasoning, and reading comprehension, InternalInspector achieves significantly higher accuracy in aligning the estimated confidence scores with the correctness of the LLM's predictions and lower calibration error. Furthermore, InternalInspector excels at HaluEval, a hallucination detection benchmark, outperforming other internal-based confidence estimation methods in this task.
LLMs have become a go-to solution not just for text generation, but also for natural language understanding (NLU) tasks. Acquiring extensive knowledge through language modeling on web-scale corpora, they excel on English NLU, yet struggle to extend their NLU capabilities to underrepresented languages. In contrast, machine translation models (MT) produce excellent multilingual representations, resulting in strong translation performance even for low-resource languages. MT encoders, however, lack the knowledge necessary for comprehensive NLU that LLMs obtain through language modeling training on immense corpora. In this work, we get the best both worlds by integrating MT encoders directly into LLM backbones via sample-efficient self-distillation. The resulting MT-LLMs preserve the inherent multilingual representational alignment from the MT encoder, allowing lower-resource languages to tap into the rich knowledge embedded in English-centric LLMs. Merging the MT encoder and LLM in a single model, we mitigate the propagation of translation errors and inference overhead of MT decoding inherent to discrete translation-based cross-lingual transfer (e.g., translate-test). Evaluation spanning three prominent NLU tasks and 127 predominantly low-resource languages renders MT-LLMs highly effective in cross-lingual transfer. MT-LLMs substantially and consistently outperform translate-test based on the same MT model, showing that we truly unlock multilingual language understanding for LLMs.
Recent models for natural language understanding are inclined to exploit simple patterns in datasets, commonly known as shortcuts. These shortcuts hinge on spurious correlations between labels and latent features existing in the training data. At inference time, shortcut-dependent models are likely to generate erroneous predictions under distribution shifts, particularly when some latent features are no longer correlated with the labels. To avoid this, previous studies have trained models to eliminate the reliance on shortcuts. In this study, we explore a different direction: pessimistically aggregating the predictions of a mixture-of-experts, assuming each expert captures relatively different latent features. The experimental results demonstrate that our post-hoc control over the experts significantly enhances the model's robustness to the distribution shift in shortcuts. Besides, we show that our approach has some practical advantages. We also analyze our model and provide results to support the assumption.
We introduce the LiLiuM series of large language models (LLMs): 1B, 7B, and 13B parameter models developed 100% in-house to fit eBay's specific needs in the e-commerce domain. This gives eBay full control over all aspects of the models including license, data, vocabulary, and architecture. We expect these models to be used as a foundation for fine-tuning and instruction-tuning, eliminating dependencies to external models. The LiLiuM LLMs have been trained on 3 trillion tokens of multilingual text from general and e-commerce domain. They perform similar to the popular LLaMA-2 models on English natural language understanding (NLU) benchmarks. At the same time, we outperform LLaMA-2 on non-English NLU tasks, machine translation and on e-commerce specific downstream tasks. As part of our data mixture, we utilize the newly released RedPajama-V2 dataset for training and share our insights regarding data filtering and deduplication. We also discuss in detail how to serialize structured data for use in autoregressive language modeling. We provide insights on the effects of including code and parallel machine translation data in pre-training. Furthermore, we develop our own tokenizer and model vocabulary, customized towards e-commerce. This way, we can achieve up to 34% speed-up in text generation on eBay-specific downstream tasks compared to LLaMA-2. Finally, in relation to LLM pretraining, we show that checkpoint averaging can further improve over the best individual model checkpoint.
Low-rank adaptation (LoRA) has become the default approach to fine-tune large language models (LLMs) due to its significant reduction in trainable parameters. However, trainable parameter demand for LoRA increases with increasing model embedding dimensions, leading to high compute costs. Additionally, its backward updates require storing high-dimensional intermediate activations and optimizer states, demanding high peak GPU memory. In this paper, we introduce large model fine-tuning via spectrally decomposed low-dimensional adaptation (LaMDA), a novel approach to fine-tuning large language models, which leverages low-dimensional adaptation to achieve significant reductions in trainable parameters and peak GPU memory footprint. LaMDA freezes a first projection matrix (PMA) in the adaptation path while introducing a low-dimensional trainable square matrix, resulting in substantial reductions in trainable parameters and peak GPU memory usage. LaMDA gradually freezes a second projection matrix (PMB) during the early fine-tuning stages, reducing the compute cost associated with weight updates to enhance parameter efficiency further. We also present an enhancement, LaMDA++, incorporating a ``lite-weight" adaptive rank allocation for the LoRA path via normalized spectrum analysis of pre-trained model weights. We evaluate LaMDA/LaMDA++ across various tasks, including natural language understanding with the GLUE benchmark, text summarization, natural language generation, and complex reasoning on different LLMs. Results show that LaMDA matches or surpasses the performance of existing alternatives while requiring up to 17.7x fewer parameter updates and up to 1.32x lower peak GPU memory usage during fine-tuning. Code will be publicly available.
We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardized corpus of 240T tokens extracted from Common Crawl, effective pretraining recipes based on the OpenLM framework, and a broad suite of 53 downstream evaluations. Participants in the DCLM benchmark can experiment with data curation strategies such as deduplication, filtering, and data mixing at model scales ranging from 412M to 7B parameters. As a baseline for DCLM, we conduct extensive experiments and find that model-based filtering is key to assembling a high-quality training set. The resulting dataset, DCLM-Baseline enables training a 7B parameter language model from scratch to 64% 5-shot accuracy on MMLU with 2.6T training tokens. Compared to MAP-Neo, the previous state-of-the-art in open-data language models, DCLM-Baseline represents a 6.6 percentage point improvement on MMLU while being trained with 40% less compute. Our baseline model is also comparable to Mistral-7B-v0.3 and Llama 3 8B on MMLU (63% & 66%), and performs similarly on an average of 53 natural language understanding tasks while being trained with 6.6x less compute than Llama 3 8B. Our results highlight the importance of dataset design for training language models and offer a starting point for further research on data curation.
Recent advancements in language and vision assistants have showcased impressive capabilities but suffer from a lack of transparency, limiting broader research and reproducibility. While open-source models handle general image tasks effectively, they face challenges with the high computational demands of complex visually-situated text understanding. Such tasks often require increased token inputs and large vision modules to harness high-resolution information. Striking a balance between model size and data importance remains an open question. This study aims to redefine the design of vision-language models by identifying key components and creating efficient models with constrained inference costs. By strategically formulating datasets, optimizing vision modules, and enhancing supervision techniques, we achieve significant improvements in inference throughput while maintaining high performance. Extensive experiments across models ranging from 160M to 13B parameters offer insights into model optimization. We will fully open-source our codebase, models, and datasets at https://github.com/naver-ai/elva.
Large language models like GPT have proven widely successful on natural language understanding tasks based on written text documents. In this paper, we investigate an LLM's performance on recordings of a group oral communication task in which utterances are often truncated or not well-formed. We propose a new group task experiment involving a puzzle with several milestones that can be achieved in any order. We investigate methods for processing transcripts to detect if, when, and by whom a milestone has been completed. We demonstrate that iteratively prompting GPT with transcription chunks outperforms semantic similarity search methods using text embeddings, and further discuss the quality and randomness of GPT responses under different context window sizes.
This paper introduces CodeGemma, a collection of specialized open code models built on top of Gemma, capable of a variety of code and natural language generation tasks. We release three model variants. CodeGemma 7B pretrained (PT) and instruction-tuned (IT) variants have remarkably resilient natural language understanding, excel in mathematical reasoning, and match code capabilities of other open models. CodeGemma 2B is a state-of-the-art code completion model designed for fast code infilling and open-ended generation in latency-sensitive settings.