We introduce a novel method for real-time animation control and generation on rigged models using natural language input. First, we embed a large language model (LLM) in Unity to output structured texts that can be parsed into diverse and realistic animations. Second, we illustrate LLM's potential to enable flexible state transition between existing animations. We showcase the robustness of our approach through qualitative results on various rigged models and motions.

Large language models (LLMs) are typically evaluated on the basis of task-based benchmarks such as MMLU. Such benchmarks do not examine responsible behaviour of LLMs in specific contexts. This is particularly true in the LGBTI+ context where social stereotypes may result in variation in LGBTI+ terminology. Therefore, domain-specific lexicons or dictionaries may be useful as a representative list of words against which the LLM's behaviour needs to be evaluated. This paper presents a methodology for evaluation of LLMs using an LGBTI+ lexicon in Indian languages. The methodology consists of four steps: formulating NLP tasks relevant to the expected behaviour, creating prompts that test LLMs, using the LLMs to obtain the output and, finally, manually evaluating the results. Our qualitative analysis shows that the three LLMs we experiment on are unable to detect underlying hateful content. Similarly, we observe limitations in using machine translation as means to evaluate natural language understanding in languages other than English. The methodology presented in this paper can be useful for LGBTI+ lexicons in other languages as well as other domain-specific lexicons. The work done in this paper opens avenues for responsible behaviour of LLMs, as demonstrated in the context of prevalent social perception of the LGBTI+ community.

An important assumption that comes with using LLMs on psycholinguistic data has gone unverified. LLM-based predictions are based on subword tokenization, not decomposition of words into morphemes. Does that matter? We carefully test this by comparing surprisal estimates using orthographic, morphological, and BPE tokenization against reading time data. Our results replicate previous findings and provide evidence that in the aggregate, predictions using BPE tokenization do not suffer relative to morphological and orthographic segmentation. However, a finer-grained analysis points to potential issues with relying on BPE-based tokenization, as well as providing promising results involving morphologically-aware surprisal estimates and suggesting a new method for evaluating morphological prediction.

We present a framework for the automated measurement of responsible AI (RAI) metrics for large language models (LLMs) and associated products and services. Our framework for automatically measuring harms from LLMs builds on existing technical and sociotechnical expertise and leverages the capabilities of state-of-the-art LLMs, such as GPT-4. We use this framework to run through several case studies investigating how different LLMs may violate a range of RAI-related principles. The framework may be employed alongside domain-specific sociotechnical expertise to create measurements for new harm areas in the future. By implementing this framework, we aim to enable more advanced harm measurement efforts and further the responsible use of LLMs.

Making big purchases requires consumers to research or consult a salesperson to gain domain expertise. However, existing conversational recommender systems (CRS) often overlook users' lack of background knowledge, focusing solely on gathering preferences. In this work, we define a new problem space for conversational agents that aim to provide both product recommendations and educational value through mixed-type mixed-initiative dialog. We introduce SalesOps, a framework that facilitates the simulation and evaluation of such systems by leveraging recent advancements in large language models (LLMs). We build SalesBot and ShopperBot, a pair of LLM-powered agents that can simulate either side of the framework. A comprehensive human study compares SalesBot against professional salespeople, revealing that although SalesBot approaches professional performance in terms of fluency and informativeness, it lags behind in recommendation quality. We emphasize the distinct limitations both face in providing truthful information, highlighting the challenges of ensuring faithfulness in the CRS context. We release our code and make all data available.

We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as input text instructions and visual egocentric observations and output actions directly in the environment. Using reinforcement learning, we train LLaRP to see and act solely through environmental interactions. We show that LLaRP is robust to complex paraphrasings of task instructions and can generalize to new tasks that require novel optimal behavior. In particular, on 1,000 unseen tasks it achieves 42% success rate, 1.7x the success rate of other common learned baselines or zero-shot applications of LLMs. Finally, to aid the community in studying language conditioned, massively multi-task, embodied AI problems we release a novel benchmark, Language Rearrangement, consisting of 150,000 training and 1,000 testing tasks for language-conditioned rearrangement. Video examples of LLaRP in unseen Language Rearrangement instructions are at https://llm-rl.github.io.

With advancements in natural language processing (NLP) models, automatic explanation generation has been proposed to mitigate misinformation on social media platforms in addition to adding warning labels to identified fake news. While many researchers have focused on generating good explanations, how these explanations can really help humans combat fake news is under-explored. In this study, we compare the effectiveness of a warning label and the state-of-the-art counterfactual explanations generated by GPT-4 in debunking misinformation. In a two-wave, online human-subject study, participants (N = 215) were randomly assigned to a control group in which false contents are shown without any intervention, a warning tag group in which the false claims were labeled, or an explanation group in which the false contents were accompanied by GPT-4 generated explanations. Our results show that both interventions significantly decrease participants' self-reported belief in fake claims in an equivalent manner for the short-term and long-term. We discuss the implications of our findings and directions for future NLP-based misinformation debunking strategies.

Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM) to evaluate LLMs efficiently and effectively in open-ended benchmarks. We first propose a comprehensive, large-scale, high-quality dataset containing task seeds, LLMs-generated answers, and GPT-4-generated judgments for fine-tuning high-performance judges, as well as a new benchmark for evaluating the judges. We train JudgeLM at different scales from 7B, 13B, to 33B parameters, and conduct a systematic analysis of its capabilities and behaviors. We then analyze the key biases in fine-tuning LLM as a judge and consider them as position bias, knowledge bias, and format bias. To address these issues, JudgeLM introduces a bag of techniques including swap augmentation, reference support, and reference drop, which clearly enhance the judge's performance. JudgeLM obtains the state-of-the-art judge performance on both the existing PandaLM benchmark and our proposed new benchmark. Our JudgeLM is efficient and the JudgeLM-7B only needs 3 minutes to judge 5K samples with 8 A100 GPUs. JudgeLM obtains high agreement with the teacher judge, achieving an agreement exceeding 90% that even surpasses human-to-human agreement. JudgeLM also demonstrates extended capabilities in being judges of the single answer, multimodal models, multiple answers, and multi-turn chat.

Instruction-based language modeling has received significant attention in pretrained language models. However, the efficiency of instruction engineering remains low and hinders the development of instruction studies. Recent studies have focused on automating instruction generation, but they primarily aim to improve performance without considering other crucial objectives that impact instruction quality, such as instruction length and perplexity. Therefore, we propose a novel approach (i.e., InstOptima) that treats instruction generation as an evolutionary multi-objective optimization problem. In contrast to text edition-based methods, our approach utilizes a large language model (LLM) to simulate instruction operators, including mutation and crossover. Furthermore, we introduce an objective-guided mechanism for these operators, allowing the LLM to comprehend the objectives and enhance the quality of the generated instructions. Experimental results demonstrate improved fine-tuning performance and the generation of a diverse set of high-quality instructions.

This paper reports on a set of three recent experiments utilizing large-scale speech models to evaluate the oral reading fluency (ORF) of students in Ghana. While ORF is a well-established measure of foundational literacy, assessing it typically requires one-on-one sessions between a student and a trained evaluator, a process that is time-consuming and costly. Automating the evaluation of ORF could support better literacy instruction, particularly in education contexts where formative assessment is uncommon due to large class sizes and limited resources. To our knowledge, this research is among the first to examine the use of the most recent versions of large-scale speech models (Whisper V2 wav2vec2.0) for ORF assessment in the Global South. We find that Whisper V2 produces transcriptions of Ghanaian students reading aloud with a Word Error Rate of 13.5. This is close to the model's average WER on adult speech (12.8) and would have been considered state-of-the-art for children's speech transcription only a few years ago. We also find that when these transcriptions are used to produce fully automated ORF scores, they closely align with scores generated by expert human graders, with a correlation coefficient of 0.96. Importantly, these results were achieved on a representative dataset (i.e., students with regional accents, recordings taken in actual classrooms), using a free and publicly available speech model out of the box (i.e., no fine-tuning). This suggests that using large-scale speech models to assess ORF may be feasible to implement and scale in lower-resource, linguistically diverse educational contexts.