Active Learning aims to minimize annotation effort by selecting the most useful instances from a pool of unlabeled data. However, typical active learning methods overlook the presence of distinct example groups within a class, whose prevalence may vary, e.g., in occupation classification datasets certain demographics are disproportionately represented in specific classes. This oversight causes models to rely on shortcuts for predictions, i.e., spurious correlations between input attributes and labels occurring in well-represented groups. To address this issue, we propose Active Learning Via INterpolation (ALVIN), which conducts intra-class interpolations between examples from under-represented and well-represented groups to create anchors, i.e., artificial points situated between the example groups in the representation space. By selecting instances close to the anchors for annotation, ALVIN identifies informative examples exposing the model to regions of the representation space that counteract the influence of shortcuts. Crucially, since the model considers these examples to be of high certainty, they are likely to be ignored by typical active learning methods. Experimental results on six datasets encompassing sentiment analysis, natural language inference, and paraphrase detection demonstrate that ALVIN outperforms state-of-the-art active learning methods in both in-distribution and out-of-distribution generalization.
论文检索
输入标题、作者或关键词，从 7,591 篇学术成果中精准定位
Loss spikes, a phenomenon in which the loss value diverges suddenly, is a fundamental issue in the pre-training of large language models. This paper supposes that the non-uniformity of the norm of the parameters is one of the causes of loss spikes. Here, in training of neural networks, the scale of the gradients is required to be kept constant throughout the layers to avoid the vanishing and exploding gradients problem. However, to meet these requirements in the Transformer model, the norm of the model parameters must be non-uniform, and thus, parameters whose norm is smaller are more sensitive to the parameter update. To address this issue, we propose a novel technique, weight scaling as reparameterization (WeSaR). WeSaR introduces a gate parameter per parameter matrix and adjusts it to the value satisfying the requirements. Because of the gate parameter, WeSaR sets the norm of the original parameters uniformly, which results in stable training. Experimental results with the Transformer decoders consisting of 130 million, 1.3 billion, and 13 billion parameters showed that WeSaR stabilizes and accelerates training and that it outperformed compared methods including popular initialization methods.
While recent years have seen rapid progress in image-conditioned text generation, image captioning still suffers from the fundamental issue of hallucinations, namely, the generation of spurious details that cannot be inferred from the given image. Existing methods largely use closed-vocabulary object lists to mitigate or evaluate hallucinations in image captioning, ignoring the long-tailed nature of hallucinations that occur in practice. To this end, we propose a framework for addressing hallucinations in image captioning in the open-vocabulary setting. Our framework includes a new benchmark, OpenCHAIR, that leverages generative foundation models to evaluate open-vocabulary object hallucinations for image captioning, surpassing the popular and similarly-sized CHAIR benchmark in both diversity and accuracy. Furthermore, to mitigate open-vocabulary hallucinations without using a closed object list, we propose MOCHa, an approach harnessing advancements in reinforcement learning. Our multi-objective reward function explicitly targets the trade-off between fidelity and adequacy in generations without requiring any strong supervision. MOCHa improves a large variety of image captioning models, as captured by our OpenCHAIR benchmark and other existing metrics. We will release our code and models.
‘Quis custodiet ipsos custodes?’ Who will watch the watchmen? On Detecting AI-generated peer-reviews
PDF ↗The integrity of the peer-review process is vital for maintaining scientific rigor and trust within the academic community. With the steady increase in the usage of large language models (LLMs) like ChatGPT in academic writing, there is a growing concern that AI-generated texts could compromise the scientific publishing including peer-reviews. Previous works have focused on generic AI-generated text detection or have presented an approach for estimating the fraction of peer-reviews that can be AI-generated. Our focus here is to solve a real-world problem by assisting the editor or chair in determining whether a review is written by ChatGPT or not. To address this, we introduce the Term Frequency (TF) model, which posits that AI often repeats tokens, and the Review Regeneration (RR) model which is based on the idea that ChatGPT generates similar outputs upon re-prompting. We stress test these detectors against token attack and paraphrasing. Finally we propose an effective defensive strategy to reduce the effect of paraphrasing on our models. Our findings suggest both our proposed methods perform better than other AI text detectors. Our RR model is more robust, although our TF model performs better than the RR model without any attacks. We make our code, dataset, model public.
Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge. Model editing emerges as a promising solution to address these challenges. However, existing editing methods struggle to track and incorporate changes in knowledge associated with edits, which limits the generalization ability of post-edit LLMs in processing edited knowledge. To tackle these problems, we propose a novel model editing method that leverages knowledge graphs for enhancing LLM editing, namely GLAME. Specifically, we first utilize a knowledge graph augmentation module to uncover associated knowledge that has changed due to editing, obtaining its internal representations within LLMs. This approach allows knowledge alterations within LLMs to be reflected through an external graph structure. Subsequently, we design a graph-based knowledge edit module to integrate structured knowledge into the model editing. This ensures that the updated parameters reflect not only the modifications of the edited knowledge but also the changes in other associated knowledge resulting from the editing process. Comprehensive experiments conducted on GPT-J and GPT-2 XL demonstrate that GLAME significantly improves the generalization capabilities of post-edit LLMs in employing edited knowledge.
Watermarking enables people to determine whether the text is generated by a specific model. It injects a unique signature based on the “green-red” list that can be tracked during detection, where the words in green lists are encouraged to be generated. Recent researchers propose to fix the green/red lists or increase the proportion of green tokens to defend against paraphrasing attacks. However, these methods cause degradation of text quality due to semantic disparities between the watermarked text and the unwatermarked text. In this paper, we propose a semantic-aware watermark method that considers contexts to generate a semantic-aware key to split a semantically balanced green/red list for watermark injection. The semantic balanced list reduces the performance drop due to adding bias on green lists. To defend against paraphrasing attacks, we generate the watermark key considering the semantics of contexts via locally sensitive hashing. To improve the text quality, we propose to split green/red lists considering semantics to enable the green list to cover almost all semantics. We also dynamically adapt the bias to balance text quality and robustness. The experiments show our advantages in both robustness and text quality comparable to existing baselines.
LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering
PDF ↗Long-Context Question Answering (LCQA), a challenging task, aims to reason over long-context documents to yield accurate answers to questions. Existing long-context Large Language Models (LLMs) for LCQA often struggle with the “lost in the middle” issue. Retrieval-Augmented Generation (RAG) mitigates this issue by providing external factual evidence. However, its chunking strategy disrupts the global long-context information, and its low-quality retrieval in long contexts hinders LLMs from identifying effective factual details due to substantial noise. To this end, we propose LongRAG, a general, dual-perspective, and robust LLM-based RAG system paradigm for LCQA to enhance RAG’s understanding of complex long-context knowledge (i.e., global information and factual details). We design LongRAG as a plug-and-play paradigm, facilitating adaptation to various domains and LLMs. Extensive experiments on three multi-hop datasets demonstrate that LongRAG significantly outperforms long-context LLMs (up by 6.94%), advanced RAG (up by 6.16%), and Vanilla RAG (up by 17.25%). Furthermore, we conduct quantitative ablation studies and multi-dimensional analyses, highlighting the effectiveness of the system’s components and fine-tuning strategies.Data and code are available at [https://github.com/QingFei1/LongRAG](https://github.com/QingFei1/LongRAG).
Rethinking Pragmatics in Large Language Models: Towards Open-Ended Evaluation and Preference Tuning
PDF ↗This study addresses the challenges of assessing and enhancing social-pragmatic inference in large language models (LLMs). We first highlight the inadequacy of current accuracy-based multiple choice question answering (MCQA) formats in assessing social-pragmatic reasoning, and propose the direct evaluation of models’ free-form responses as measure, which correlates better with human judgment. Furthermore, we explore methods to improve pragmatic abilities in LLMs, advocating for preference optimization (PO) over supervised finetuning (SFT), given the absence of a definitive “gold” answer in social contexts. Our results show that preferential tuning consistently outperforms SFT across pragmatic phenomena and offers a near-free launch in pragmatic abilities without compromising general capabilities. Lastly, we examine the internal structure of LLMs, revealing that the significant boost in pragmatic reasoning is tied to deeper layer representations, analogous to human high-level thinking. Our experiments span a variety of pragmatic and social reasoning datasets, as well as an image referential game requiring a multimodal theory of mind (ToM). With our refined paradigms for evaluating and enhancing pragmatic inference, this paper offers key insights into building more socially aware language models.
Multimodal models leverage large-scale pretraining to achieve strong but still imperfect performance on tasks such as image captioning, visual question answering, and cross-modal retrieval. In this paper, we present a simple and efficient method for correcting errors in trained contrastive image-text retrieval models with no additional training, called Nearest Neighbor Normalization (NNN). We show an improvement on retrieval metrics in both text retrieval and image retrieval for all of the contrastive models that we tested (CLIP, BLIP, ALBEF, SigLIP, BEiT) and for both of the datasets that we used (MS-COCO and Flickr30k). NNN requires a reference database, but does not require any training on this database, and can even increase the retrieval accuracy of a model after finetuning.
Deciphering Cognitive Distortions in Patient-Doctor Mental Health Conversations: A Multimodal LLM-Based Detection and Reasoning Framework
PDF ↗Cognitive distortion research holds increasing significance as it sheds light on pervasive errors in thinking patterns, providing crucial insights into mental health challenges and fostering the development of targeted interventions and therapies. This paper delves into the complex domain of cognitive distortions which are prevalent distortions in cognitive processes often associated with mental health issues. Focusing on patient-doctor dialogues, we introduce a pioneering method for detecting and reasoning about cognitive distortions utilizing Large Language Models (LLMs). Operating within a multimodal context encompassing audio, video, and textual data, our approach underscores the critical importance of integrating diverse modalities for a comprehensive understanding of cognitive distortions. By leveraging multimodal information, including audio, video, and textual data, our method offers a nuanced perspective that enhances the accuracy and depth of cognitive distortion detection and reasoning in a zero-shot manner. Our proposed hierarchical framework adeptly tackles both detection and reasoning tasks, showcasing significant performance enhancements compared to current methodologies. Through comprehensive analysis, we elucidate the efficacy of our approach, offering promising insights into the diagnosis and understanding of cognitive distortions in multimodal settings.The code and dataset can be found here: https://github.com/clang1234/ZS-CoDR.git
While instruction fine-tuned LLMs are effective text generators, sensitivity to prompt construction makes performance unstable and sub-optimal in practice. Relying on a single ‘best’ prompt cannot capture all differing approaches to a generation problem. Using this observation, we propose multi-prompt decoding, where many candidate generations are decoded from a prompt bank at inference-time. To ensemble candidates, we use Minimum Bayes Risk (MBR) decoding, which selects a final output using a trained value metric. We show multi-prompt improves MBR across a comprehensive set of conditional generation tasks, and show this is a result of estimating a more diverse and higher quality candidate space than that of a single prompt. Our experiments confirm multi-prompt improves generation across tasks, models and metrics.
Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code
PDF ↗This paper presents Coffee-Gym, a comprehensive RL environment for training models that provide feedback on code editing. Coffee-Gym includes two major components: (1) Coffee, a dataset containing humans’ code edit traces for coding questions and human-written feedback for editing erroneous code; (2) CoffeeEval, a reward function that faithfully reflects the helpfulness of feedback by assessing the performance of the revised code in unit tests. With them, Coffee-Gym addresses the unavailability of high-quality datasets for training feedback models with RL, and provides more accurate rewards than the SOTA reward model (i.e., GPT-4). By applying Coffee-Gym, we elicit feedback models that outperform baselines in enhancing open-source code LLMs’ code editing, making them comparable with closed-source LLMs. We make the dataset and the model checkpoint publicly available in https://huggingface.co/spaces/Coffee-Gym/Project-Coffee-Gym.
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models
PDF ↗Algorithmic reasoning tasks that involve complex logical patterns, such as completing Dyck language, pose challenges for large language models (LLMs), despite their recent success. Prior work has used LLMs to generate programming language and applied external compilers for such tasks. Yet, when on the fly, it is hard to generate an executable code with the correct logic for the solution. Even so, code for one instance cannot be reused for others, although they might require the same logic to solve. We present Think-and-Execute, a novel framework that improves LLMs’ algorithmic reasoning: (1) In Think, we discover task-level logic shared across all instances, and express such logic with pseudocode; (2) In Execute, we tailor the task-level pseudocode to each instance and simulate the execution of it. Think-and-Execute outperforms several strong baselines (including CoT and PoT) in diverse algorithmic reasoning tasks. We manifest the advantage of using task-level pseudocode over generating instance-specific solutions one by one. Also, we show that pseudocode can better improve LMs’ reasoning than natural language (NL) guidance, even though they are trained with NL instructions.
In today’s dynamic world, providing inclusive and personalized support for individuals with physical disabilities is imperative. With diverse needs and preferences, tailored assistance according to user personas is crucial. In this paper, we introduce ABLE (Adaptive, Bespoke, Listen and Empathetic), a Conversational Support System for Physical Disabilities. By tracking user personas, including gender, age, and personality traits based on the OCEAN model, ABLE ensures that support interactions are uniquely tailored to each user’s characteristics and preferences. Moreover, integrating politeness and empathy levels in responses enhances user satisfaction and engagement, fostering a supportive and respectful environment. The development of ABLE involves compiling a comprehensive conversational dataset enriched with user profile annotations. Leveraging reinforcement learning techniques and diverse reward mechanisms, ABLE trains a model to generate responses aligned with individual user profiles while maintaining appropriate levels of politeness and empathy. Based on rigorous empirical analysis encompassing automatic and human evaluation metrics based on persona-consistency, politeness accuracy, empathy accuracy, perplexity, and conversation coherence, the efficacy of ABLE is assessed. Our findings underscore ABLE’s success in delivering tailored support to individuals grappling with physical disabilities. To the best of our knowledge, this is the very first attempt towards building a user’s persona-oriented physical disability support system.
Current Large Language Models (LLMs) have shown strong reasoning capabilities in commonsense question answering benchmarks, but the process underlying their success remains largely opaque. As a consequence, recent approaches have equipped LLMs with mechanisms for knowledge retrieval, reasoning and introspection, not only to improve their capabilities but also to enhance the interpretability of their outputs. However, these methods require additional training, hand-crafted templates or human-written explanations. To address these issues, we introduce ZEBRA, a zero-shot question answering framework that combines retrieval, case-based reasoning and introspection and dispenses with the need for additional training of the LLM. Given an input question, ZEBRA retrieves relevant question-knowledge pairs from a knowledge base and generates new knowledge by reasoning over the relationships in these pairs. This generated knowledge is then used to answer the input question, improving the model’s performance and interpretability. We evaluate our approach across 8 well-established commonsense reasoning benchmarks, demonstrating that ZEBRA consistently outperforms strong LLMs and previous knowledge integration approaches, achieving an average accuracy improvement of up to 4.5 points.
Built on the power of LLMs, numerous multimodal large language models (MLLMs) have recently achieved remarkable performance on various vision-language tasks. However, most existing MLLMs and benchmarks primarily focus on single-image input scenarios, leaving the performance of MLLMs when handling realistic multiple images underexplored. Although a few benchmarks consider multiple images, their evaluation dimensions and samples are very limited. In this paper, we propose a new benchmark MIBench, to comprehensively evaluate fine-grained abilities of MLLMs in multi-image scenarios. Specifically, MIBench categorizes the multi-image abilities into three scenarios: multi-image instruction (MII), multimodal knowledge-seeking (MKS) and multimodal in-context learning (MIC), and constructs 13 tasks with a total of 13K annotated samples. During data construction, for MII and MKS, we extract correct options from manual annotations and create challenging distractors to obtain multiple-choice questions. For MIC, to enable an in-depth evaluation, we set four sub-tasks and transform the original datasets into in-context learning formats. We evaluate several open-source and closed-source MLLMs on the proposed MIBench. The results reveal that although current models excel in single-image tasks, they exhibit significant shortcomings when faced with multi-image inputs, such as limited fine-grained perception, multi-image reasoning and in-context learning abilities. The annotated data of MIBench is available at https://huggingface.co/datasets/StarBottle/MIBench.
Recently, enabling pretrained language models (PLMs) to perform zero-shot crossmodal tasks such as video question answering has been extensively studied. A popular approach is to learn a projection network that projects visual features into the input text embedding space of a PLM, as well as feed-forward adaptation layers, with the weights of the PLM frozen. However, is it really necessary to learn such additional layers? In this paper, we make the first attempt to demonstrate that the PLM is able to perform zero-shot crossmodal tasks without any crossmodal pretraining, when the observed visual concepts are injected as both additional input text tokens and augmentation in the intermediate features within each feed-forward network for the PLM. Specifically, inputting observed visual concepts as text tokens helps to inject them through the self-attention layers in the PLM; to augment the intermediate features in a way that is compatible with the PLM, we propose to construct adaptation layers based on the intermediate representation of concepts (obtained by solely inputting them to the PLM). These two complementary injection mechanisms form the proposed Deep Concept Injection, which comprehensively enables the PLM to perceive instantly without crossmodal pretraining. Extensive empirical analysis on zero-shot video question answering, as well as visual question answering, shows Deep Concept Injection achieves competitive or even better results in both zero-shot and fine-tuning settings, compared to state-of-the-art methods that require crossmodal pretraining.
Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair
PDF ↗In Simultaneous Machine Translation (SiMT), training with a simultaneous interpretation (SI) corpus is an effective method for achieving high-quality yet low-latency. However, constructing such a corpus is challenging due to high costs, and limitations in annotator capabilities, and as a result, existing SI corpora are limited. Therefore, we propose a method to convert existing speech translation (ST) corpora into interpretation-style corpora, maintaining the original word order and preserving the entire source content using Large Language Models (LLM-SI-Corpus). We demonstrate that fine-tuning SiMT models using the LLM-SI-Corpus reduces latency while achieving better quality compared to models fine-tuned with other corpora in both speech-to-text and text-to-text settings. The LLM-SI-Corpus is available at https://github.com/yusuke1997/LLM-SI-Corpus.
Causal reasoning is fundamental to human intelligence and crucial for effective decision-making in real-world environments. Despite recent advancements in large vision-language models (LVLMs), their ability to comprehend causality remains unclear. Previous work typically focuses on commonsense causality between events and/or actions, which is insufficient for applications like embodied agents and lacks the explicitly defined causal graphs required for formal causal reasoning. To overcome these limitations, we introduce a fine-grained and unified definition of causality involving interactions between humans and/or objects. Building on the definition, we construct a novel dataset, CELLO, consisting of 14,094 causal questions across all four levels of causality: discovery, association, intervention, and counterfactual. This dataset surpasses traditional commonsense causality by including explicit causal graphs that detail the interactions between humans and objects. Extensive experiments on CELLO reveal that current LVLMs still struggle with causal reasoning tasks, but they can benefit significantly from our proposed CELLO-CoT, a causally inspired chain-of-thought prompting strategy. Both quantitative and qualitative analyses from this study provide valuable insights for future research. Our project page is at https://github.com/OpenCausaLab/CELLO.
SimLLM: Detecting Sentences Generated by Large Language Models Using Similarity between the Generation and its Re-generation
PDF ↗Large language models have emerged as a significant phenomenon due to their ability to produce natural text across various applications. However, the proliferation of generated text raises concerns regarding its potential misuse in fraudulent activities such as academic dishonesty, spam dissemination, and misinformation propagation. Prior studies have detected the generation of non-analogous text, which manifests numerous differences between original and generated text. We have observed that the similarity between the original text and its generation is notably higher than that between the generated text and its subsequent regeneration. To address this, we propose a novel approach named SimLLM, aimed at estimating the similarity between an input sentence and its generated counterpart to detect analogous machine-generated sentences that closely mimic human-written ones. Our empirical analysis demonstrates SimLLM’s superior performance compared to existing methods.