Offensive speech detection is a key component of content moderation. However, what is offensive can be highly subjective. This paper investigates how machine and human moderators disagree on what is offensive when it comes to real-world social web political discourse. We show that (1) there is extensive disagreement among the moderators (humans and machines); and (2) human and large-language-model classifiers are unable to predict how other human raters will respond, based on their political leanings. For (1), we conduct a ***noise audit*** at an unprecedented scale that combines both machine and human responses. For (2), we introduce a first-of-its-kind dataset of ***vicarious offense***. Our noise audit reveals that moderation outcomes vary wildly across different machine moderators. Our experiments with human moderators suggest that political leanings combined with sensitive issues affect both first-person and vicarious offense. The dataset is available through https://github.com/Homan-Lab/voiced.

Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive | VIDEO

Human feedback is increasingly used to steer the behaviours of Large Language Models (LLMs). However, it is unclear how to collect and incorporate feedback in a way that is efficient, effective and unbiased, especially for highly subjective human preferences and values. In this paper, we survey existing approaches for learning from human feedback, drawing on 95 papers primarily from the ACL and arXiv repositories. First, we summarise the past, pre-LLM trends for integrating human feedback into language models. Second, we give an overview of present techniques and practices, as well as the motivations for using feedback; conceptual frameworks for defining values and preferences; and how feedback is collected and from whom. Finally, we encourage a better future of feedback learning in LLMs by raising five unresolved conceptual and practical challenges.

The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values | VIDEO

Recent work has shown the promise of learning with human feedback paradigms to produce human-determined high-quality text. Existing works use human feedback to train large language models (LLMs) in general domain abstractive summarization and have obtained summary quality exceeding traditional likelihood training. In this paper, we focus on a less explored form of human feedback -- Human Edits. We propose Sequence Alignment (un)Likelihood Training (SALT), a novel technique to use both the human-edited and model-generated data together in the training loop. In addition, we demonstrate simulating Human Edits with ground truth summaries coming from existing training data -- Imitation edits, along with the model-generated summaries obtained after the training, to reduce the need for expensive human-edit data. In our experiments, we extend human feedback exploration from general domain summarization to medical domain summarization. Our results demonstrate the effectiveness of SALT in improving the summary quality with Human and Imitation Edits. Through additional experiments, we show that SALT outperforms the conventional RLHF method (designed for human preferences) -- DPO, when applied to human-edit data. We hope the evidence in our paper prompts researchers to explore, collect, and better use different human feedback approaches scalably.

Improving Summarization with Human Edits | VIDEO

Evaluating conversational information retrieval (CIR) systems is a challenging task that requires a significant amount of human labor for annotation. It is imperative to invest significant effort into researching more labor-effective methods for evaluating CIR systems. To touch upon this challenge, we take the first step to involve active testing in CIR evaluation and propose a novel method, called HomCoE. It strategically selects a few data for human annotation, then calibrates the evaluation results to eliminate evaluation biases. As such, it makes an accurate evaluation of the CIR system at low human labor. We experimentally reveal that it consumes less than 1\% of human labor and achieves a consistency rate of 95\%-99\% with human evaluation results. This emphasizes the superiority of our method over other baselines.

Reduce Human Labor On Evaluating Conversational Information Retrieval System: A Human-Machine Collaboration Approach | VIDEO

Existing lexical substitution (LS) benchmarks were collected by asking human annotators to think of substitutes from memory, resulting in benchmarks with limited coverage and relatively small scales. To overcome this problem, we propose a novel annotation method to construct an LS dataset based on human and machine collaboration. Based on our annotation method, we construct the first Chinese LS dataset CHNLS which consists of 33,695 instances and 144,708 substitutes, covering three text genres (News, Novel, and Wikipedia). Specifically, we first combine four unsupervised LS methods as an ensemble method to generate the candidate substitutes, and then let human annotators judge these candidates or add new ones. This collaborative process combines the diversity of machine-generated substitutes with the expertise of human annotators. Experimental results that the ensemble method outperforms other LS methods. To our best knowledge, this is the first study for the Chinese LS task.

Chinese Lexical Substitution: Dataset and Method

Reports of human-like behaviors in foundation models are growing, with psychological theories providing enduring tools to investigate these behaviors. However, current research tends to directly apply these human-oriented tools without verifying the faithfulness of their outcomes. In this paper, we introduce a framework, RealBehavior, which is designed to characterize the humanoid behaviors of models faithfully. Beyond simply measuring behaviors, our framework assesses the faithfulness of results based on reproducibility, internal and external consistency, and generalizability. Our findings suggest that a simple application of psychological tools cannot faithfully characterize all human-like behaviors. Moreover, we discuss the impacts of aligning models with human and social values, arguing for the necessity of diversifying alignment objectives to prevent the creation of models with restricted characteristics.

RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms

Aligning large language models (LLMs) to human values has become increasingly important as it enables sophisticated steering of LLMs. However, it requires significant human demonstrations and feedback or distillation from proprietary LLMs such as ChatGPT.
In this work, we propose a novel alignment learning framework with synthetic feedback not dependent on extensive human annotations and proprietary LLMs. First, we perform reward modeling (RM) with synthetic feedback by contrasting responses from vanilla LLMs with various sizes and prompts. Then, we use the RM to simulate high-quality demonstrations to train a supervised policy and further optimize the model with reinforcement learning. Our resulting model, Aligned Language Model with Synthetic Training dataset (ALMoST), outperforms recent open-sourced models, which are trained on the outputs of InstructGPT or human-annotated demonstrations, in alignment benchmarks. In human evaluation, our model is preferred to Alpaca and Dolly-v2, 55.0% and 58.5% of the time, respectively. Further analyses demonstrate the efficacy and importance of synthetic feedback in our framework.

Aligning Large Language Models through Synthetic Feedback

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular, state-of-the-art large language models (LLMs) work at the level of tokens, not concepts.

In this work, we analyze how well contemporary LLMs capture human concepts and their structure. We then discuss ways to develop concept-aware LLMs, taking place at different stages of the pipeline.
We sketch a method for pretraining LLMs using concepts, and also explore the simpler approach that uses the output of existing LLMs. Despite its simplicity, our proof-of-concept is shown to better match human intuition, as well as improve the robustness of predictions. These preliminary results underscore the promise of concept-aware LLMs.

Towards Concept-Aware Large Language Models

Thematic analysis (TA) has been widely used
for analyzing qualitative data in many disciplines and fields. To ensure reliable analysis,
the same piece of data is typically assigned to at least two human coders. Moreover, to produce
meaningful and useful analysis, human coders
develop and deepen their data interpretation
and coding over multiple iterations, making TA
labor-intensive and time-consuming. Recently
the emerging field of large language models
(LLMs) research has shown that LLMs have
the potential replicate human-like behavior in
various tasks: in particular, LLMs outperform
crowd workers on text-annotation tasks, suggesting an opportunity to leverage LLMs on
TA. We propose a human–LLM collaboration
framework (i.e., LLM-in-the-loop) to conduct
TA with in-context learning (ICL). This framework provides the prompt to frame discussions
with a LLM (e.g., GPT-3.5) to generate the final
codebook for TA. We demonstrate the utility
of this framework using survey datasets on the
aspects of the music listening experience and
the usage of a password manager. Results of
the two case studies show that the proposed
framework yields similar coding quality to that
of human coders but reduces TA’s labor and
time demands.

LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis

Language model prompt optimization research has shown that semantically and grammatically well-formed manually crafted prompts are routinely outperformed by automatically generated token sequences with no apparent meaning or syntactic structure, including sequences of vectors from a model's embedding space. We use machine-generated prompts to probe how models respond to input that is not composed of natural language expressions. We study the behavior of models of different sizes in multiple semantic tasks in response to both continuous and discrete machine-generated prompts, and compare it to the behavior in response to human-generated natural-language prompts. Even when producing a similar output, machine-generated and human prompts trigger different response patterns through the network processing pathways, including different perplexities, different attention and output entropy distributions, and different unit activation profiles. We provide preliminary insight into the nature of the units activated by different prompt types, suggesting that only natural language prompts recruit a genuinely linguistic circuit.

Unnatural language processing: How do language models handle machine-generated prompts? | VIDEO

Concepts play a pivotal role in various human
cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular, state-of-the-art large language models
(LLMs) work at the level of tokens, not concepts.

In this work, we analyze how well contemporary LLMs capture human concepts and their structure. We then discuss ways to develop concept-aware LLMs, taking place at different stages of the pipeline. We sketch a method for
pretraining LLMs using concepts, and also explore the simpler approach that uses the output of existing LLMs. Despite its simplicity, our
proof-of-concept is shown to better match human intuition, as well as improve the robustness of predictions. These preliminary results underscore the promise of concept-aware LLMs.

Laterality has an important correlation to behavior and genetic disorders. Behavior can be observed through the brain hemispheres, and certain disorders have a unique pattern of laterality. Using the model organism, Caenorhabditis elegans, gives more insight into human laterality. C. elegans laterality is observed through gut laterality that is established in the embryonic cell rotation. During early embryonic development, the direction of the rotation between the ABar, ABal, ABpr, ABpl cells shows laterality. The presence of certain genes have an impact on the rotation and gut laterality. More specifically, this project will focus on the embryonic rotations in TBB-1. TBB-1 is an important component of the microtubule, which forms the mitotic spindle. The mitotic spindle is known for its importance in chromatid separation. The absence of TBB-1 could lead to reverse gut laterality. Observing the embryonic cell rotation in C. elegans, gives more insight into its human ortholog and disease. C. elegans gut laterality can provide an understanding of the mechanisms of human laterality, which can impact behavioral studies.

Underline digital video library

Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive | VIDEO

The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values | VIDEO

Improving Summarization with Human Edits | VIDEO

Reduce Human Labor On Evaluating Conversational Information Retrieval System: A Human-Machine Collaboration Approach | VIDEO

Chinese Lexical Substitution: Dataset and Method

RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms

Aligning Large Language Models through Synthetic Feedback

Towards Concept-Aware Large Language Models

LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis

Unnatural language processing: How do language models handle machine-generated prompts? | VIDEO

Towards Concept-Aware Large Language Models

Role of Schizophernia Associated Gene in Laterality Development