Large language models (LLMs) can understand human instructions, showing their potential for pragmatic applications beyond traditional NLP tasks. However, they still struggle with complex instructions, which can be either complex task descriptions that require multiple tasks and constraints, or complex input that contains long context, noise, heterogeneous information and multi-turn format. Due to these features, LLMs often ignore semantic constraints from task descriptions, generate incorrect formats, violate length or sample count constraints, and be unfaithful to the input text. Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions, as they are close-ended and simple. To bridge this gap, we propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically. We design eight features for complex instructions and construct a comprehensive evaluation dataset from real-world scenarios. We also establish four criteria and develop corresponding metrics, as current ones are inadequate, biased or too strict and coarse-grained. We compare the performance of representative Chinese-oriented and English-oriented models in following complex instructions through extensive experiments. Resources of CELLO are publicly available at //github.com/Abbey4799/CELLO.
相關內容
Large language models (LLMs) have shown their capability in understanding contextual and semantic information regarding appearance knowledge of instances. In this paper, we introduce a novel approach to utilize the strength of an LLM in understanding contextual appearance variations and to leverage its knowledge into a vision model (here, pedestrian detection). While pedestrian detection is considered one of crucial tasks directly related with our safety (e.g., intelligent driving system), it is challenging because of varying appearances and poses in diverse scenes. Therefore, we propose to formulate language-driven appearance knowledge units and incorporate them with visual cues in pedestrian detection. To this end, we establish description corpus which includes numerous narratives describing various appearances of pedestrians and others. By feeding them through an LLM, we extract appearance knowledge sets that contain the representations of appearance variations. After that, we perform a task-prompting process to obtain appearance knowledge units which are representative appearance knowledge guided to be relevant to a downstream pedestrian detection task. Finally, we provide plentiful appearance information by integrating the language-driven knowledge units with visual cues. Through comprehensive experiments with various pedestrian detectors, we verify the effectiveness of our method showing noticeable performance gains and achieving state-of-the-art detection performance.
Programmatic weak supervision methodologies facilitate the expedited labeling of extensive datasets through the use of label functions (LFs) that encapsulate heuristic data sources. Nonetheless, the creation of precise LFs necessitates domain expertise and substantial endeavors. Recent advances in pre-trained language models (PLMs) have exhibited substantial potential across diverse tasks. However, the capacity of PLMs to autonomously formulate accurate LFs remains an underexplored domain. In this research, we address this gap by introducing DataSculpt, an interactive framework that harnesses PLMs for the automated generation of LFs. Within DataSculpt, we incorporate an array of prompting techniques, instance selection strategies, and LF filtration methods to explore the expansive design landscape. Ultimately, we conduct a thorough assessment of DataSculpt's performance on 12 real-world datasets, encompassing a range of tasks. This evaluation unveils both the strengths and limitations of contemporary PLMs in LF design.
A line of work on Transformer-based language models such as BERT has attempted to use syntactic inductive bias to enhance the pretraining process, on the theory that building syntactic structure into the training process should reduce the amount of data needed for training. But such methods are often tested for high-resource languages such as English. In this work, we investigate whether these methods can compensate for data sparseness in low-resource languages, hypothesizing that they ought to be more effective for low-resource languages. We experiment with five low-resource languages: Uyghur, Wolof, Maltese, Coptic, and Ancient Greek. We find that these syntactic inductive bias methods produce uneven results in low-resource settings, and provide surprisingly little benefit in most cases.
When pretrained language models (LMs) are applied to discriminative tasks such as multiple-choice questions, they place probability mass on vocabulary tokens that aren't among the given answer choices. Spreading probability mass across multiple surface forms with identical meaning (such as "bath" and "bathtub") is thought to cause an underestimation of a model's true performance, referred to as the "surface form competition" (SFC) hypothesis. This has motivated the introduction of various probability normalization methods. However, many core questions remain unanswered. How do we measure SFC? Are there direct ways of reducing it, and does doing so improve task performance? We propose a mathematical formalism for SFC which allows us to quantify and bound its impact for the first time. We identify a simple method for reducing it -- namely, increasing probability mass on the given answer choices by a) including them in the prompt and b) using in-context learning with even just one example. We show this method eliminates the impact of SFC in the majority of instances. Our experiments on three diverse datasets and six LMs reveal several additional surprising findings. For example, both normalization and prompting methods for reducing SFC can be ineffective or even detrimental to task performance for some LMs. We conclude with practical insights for effectively prompting LMs for multiple-choice tasks.
Aligning large language models (LLMs) with human preferences has proven to drastically improve usability and has driven rapid adoption as demonstrated by ChatGPT. Alignment techniques such as supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) greatly reduce the required skill and domain knowledge to effectively harness the capabilities of LLMs, increasing their accessibility and utility across various domains. However, state-of-the-art alignment techniques like RLHF rely on high-quality human feedback data, which is expensive to create and often remains proprietary. In an effort to democratize research on large-scale alignment, we release OpenAssistant Conversations, a human-generated, human-annotated assistant-style conversation corpus consisting of 161,443 messages in 35 different languages, annotated with 461,292 quality ratings, resulting in over 10,000 complete and fully annotated conversation trees. The corpus is a product of a worldwide crowd-sourcing effort involving over 13,500 volunteers. Models trained on OpenAssistant Conversations show consistent improvements on standard benchmarks over respective base models. We release our code and data under a fully permissive licence.
Multi-agent systems driven by large language models (LLMs) have shown promising abilities for solving complex tasks in a collaborative manner. This work considers a fundamental problem in multi-agent collaboration: consensus seeking. When multiple agents work together, we are interested in how they can reach a consensus through inter-agent negotiation. To that end, this work studies a consensus-seeking task where the state of each agent is a numerical value and they negotiate with each other to reach a consensus value. It is revealed that when not explicitly directed on which strategy should be adopted, the LLM-driven agents primarily use the average strategy for consensus seeking although they may occasionally use some other strategies. Moreover, this work analyzes the impact of the agent number, agent personality, and network topology on the negotiation process. The findings reported in this work can potentially lay the foundations for understanding the behaviors of LLM-driven multi-agent systems for solving more complex tasks. Furthermore, LLM-driven consensus seeking is applied to a multi-robot aggregation task. This application demonstrates the potential of LLM-driven agents to achieve zero-shot autonomous planning for multi-robot collaboration tasks. Project website: westlakeintelligentrobotics.github.io/ConsensusLLM/.
Tabular data is one of the most commonly used types of data in machine learning. Despite recent advances in neural nets (NNs) for tabular data, there is still an active discussion on whether or not NNs generally outperform gradient-boosted decision trees (GBDTs) on tabular data, with several recent works arguing either that GBDTs consistently outperform NNs on tabular data, or vice versa. In this work, we take a step back and question the importance of this debate. To this end, we conduct the largest tabular data analysis to date, comparing 19 algorithms across 176 datasets, and we find that the 'NN vs. GBDT' debate is overemphasized: for a surprisingly high number of datasets, either the performance difference between GBDTs and NNs is negligible, or light hyperparameter tuning on a GBDT is more important than choosing between NNs and GBDTs. A remarkable exception is the recently-proposed prior-data fitted network, TabPFN: although it is effectively limited to training sets of size 3000, we find that it outperforms all other algorithms on average, even when randomly sampling 3000 training datapoints. Next, we analyze dozens of metafeatures to determine what properties of a dataset make NNs or GBDTs better-suited to perform well. For example, we find that GBDTs are much better than NNs at handling skewed or heavy-tailed feature distributions and other forms of dataset irregularities. Our insights act as a guide for practitioners to determine which techniques may work best on their dataset. Finally, with the goal of accelerating tabular data research, we release the TabZilla Benchmark Suite: a collection of the 36 'hardest' of the datasets we study. Our benchmark suite, codebase, and all raw results are available at //github.com/naszilla/tabzilla.
Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no consensus on the definition of "attribution", leading to many competing methods with little systematic evaluation, complicated in particular by the lack of ground truth attribution. To address this, we propose a dataset modification procedure to induce such ground truth. Using this procedure, we evaluate three common methods: saliency maps, rationales, and attentions. We identify several deficiencies and add new perspectives to the growing body of evidence questioning the correctness and reliability of these methods applied on datasets in the wild. We further discuss possible avenues for remedy and recommend new attribution methods to be tested against ground truth before deployment. The code is available at \url{//github.com/YilunZhou/feature-attribution-evaluation}.
Non-convex optimization is ubiquitous in modern machine learning. Researchers devise non-convex objective functions and optimize them using off-the-shelf optimizers such as stochastic gradient descent and its variants, which leverage the local geometry and update iteratively. Even though solving non-convex functions is NP-hard in the worst case, the optimization quality in practice is often not an issue -- optimizers are largely believed to find approximate global minima. Researchers hypothesize a unified explanation for this intriguing phenomenon: most of the local minima of the practically-used objectives are approximately global minima. We rigorously formalize it for concrete instances of machine learning problems.
Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing results in many language understanding tasks. In this paper, we conduct exhaustive experiments to investigate different fine-tuning methods of BERT on text classification task and provide a general solution for BERT fine-tuning. Finally, the proposed solution obtains new state-of-the-art results on eight widely-studied text classification datasets.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191