Evaluating Creativity and Deception in Large Language Models: A Simulation Framework for Multi-Agent Balderdash

Large Language Models (LLMs) have shown impressive capabilities in complex tasks and interactive environments, yet their creativity remains underexplored. This paper introduces a simulation framework utilizing the game Balderdash to evaluate both the creativity and logical reasoning of LLMs. In Balderdash, players generate fictitious definitions for obscure terms to deceive others while identifying correct definitions. Our framework enables multiple LLM agents to participate in this game, assessing their ability to produce plausible definitions and strategize based on game rules and history. We implemented a centralized game engine featuring various LLMs as participants and a judge LLM to evaluate semantic equivalence. Through a series of experiments, we analyzed the performance of different LLMs, examining metrics such as True Definition Ratio, Deception Ratio, and Correct Guess Ratio. The results provide insights into the creative and deceptive capabilities of LLMs, highlighting their strengths and areas for improvement. Specifically, the study reveals that infrequent vocabulary in LLMs' input leads to poor reasoning on game rules and historical context (https://github.com/ParsaHejabi/Simulation-Framework-for-Multi-Agent-Balderdash).

The American Sign Language Knowledge Graph: Infusing ASL Models with Linguistic Knowledge

Language models for American Sign Language (ASL) could make language technologies substantially more accessible to those who sign. To train models on tasks such as isolated sign recognition (ISR) and ASL-to-English translation, datasets provide annotated video examples of ASL signs. To facilitate the generalizability and explainability of these models, we introduce the American Sign Language Knowledge Graph (ASLKG), compiled from twelve sources of expert linguistic knowledge. We use the ASLKG to train neuro-symbolic models for 3 ASL understanding tasks, achieving accuracies of 91% on ISR, 14% for predicting the semantic features of unseen signs, and 36% for classifying the topic of Youtube-ASL videos.

Generating Contextually-Relevant Navigation Instructions for Blind and Low Vision People

Navigating unfamiliar environments presents significant challenges for blind and low-vision (BLV) individuals. In this work, we construct a dataset of images and goals across different scenarios such as searching through kitchens or navigating outdoors. We then investigate how grounded instruction generation methods can provide contextually-relevant navigational guidance to users in these instances. Through a sighted user study, we demonstrate that large pretrained language models can produce correct and useful instructions perceived as beneficial for BLV users. We also conduct a survey and interview with 4 BLV users and observe useful insights on preferences for different instructions based on the scenario.

Contrast Sets for Evaluating Language-Guided Robot Policies

Robot evaluations in language-guided, real world settings are time-consuming and often sample only a small space of potential instructions across complex scenes. In this work, we introduce contrast sets for robotics as an approach to make small, but specific, perturbations to otherwise independent, identically distributed (i.i.d.) test instances. We investigate the relationship between experimenter effort to carry out an evaluation and the resulting estimated test performance as well as the insights that can be drawn from performance on perturbed instances. We use contrast sets to characterize policies at reduced experimenter effort in both a simulated manipulation task and a physical robot vision-and-language navigation task. We encourage the use of contrast set evaluations as a more informative alternative to small scale, i.i.d. demonstrations on physical robots, and as a scalable alternative to industry-scale real world evaluations.

When Parts are Greater Than Sums: Individual LLM Components Can Outperform Full Models

This paper studies in-context learning (ICL) by decomposing the output of large language models into the individual contributions of attention heads and MLPs (components). We observe curious components: good-performing ones that individually do well on a classification task, even when the model performs poorly; bad-performing ones that do much worse than chance; and label-biased components that always predict the same label. We find that component accuracies are well-correlated across different demonstration sets and perturbations of prompt templates, even when the full-model accuracy varies greatly. Based on our findings, we propose component reweighting, which learns to linearly re-scale the component activations from a few labeled examples. Given 24 labeled examples, our method improves by an average of 6.0% accuracy points over 24-shot ICL across 8 tasks on Llama-2-7B. Overall, this paper both enriches our understanding of ICL and provides a practical method for improvement by examining model internals.

Language Models can Infer Action Semantics for Classical Planners from Environment Feedback

Classical planning approaches guarantee finding a set of actions that can achieve a given goal state when possible, but require an expert to specify logical action semantics that govern the dynamics of the environment. Researchers have shown that Large Language Models (LLMs) can be used to directly infer planning steps based on commonsense knowledge and minimal domain information alone, but such plans often fail on execution. We bring together the strengths of classical planning and LLM commonsense inference to perform domain induction, learning and validating action pre- and post-conditions based on closed-loop interactions with the environment itself. We propose PSALM, which leverages LLM inference to heuristically complete partial plans emitted by a classical planner given partial domain knowledge, as well as to infer the semantic rules of the domain in a logical language based on environment feedback after execution. Our analysis on 7 environments shows that with just one expert-curated example plans, using LLMs as heuristic planners and rule predictors achieves lower environment execution steps and environment resets than random exploration while simultaneously recovering the underlying ground truth action semantics of the domain.

TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models

Classical planning formulations like the Planning Domain Definition Language (PDDL) admit action sequences guaranteed to achieve a goal state given an initial state if any are possible. However, reasoning problems defined in PDDL do not capture temporal aspects of action taking, for example that two agents in the domain can execute an action simultaneously if postconditions of each do not interfere with preconditions of the other. A human expert can decompose a goal into largely independent constituent parts and assign each agent to one of these subgoals to take advantage of simultaneous actions for faster execution of plan steps, each using only single agent planning. By contrast, large language models (LLMs) used for directly inferring plan steps do not guarantee execution success, but do leverage commonsense reasoning to assemble action sequences. We combine the strengths of classical planning and LLMs by approximating human intuitions for two-agent planning goal decomposition. We demonstrate that LLM-based goal decomposition leads to faster planning times than solving multi-agent PDDL problems directly while simultaneously achieving fewer plan execution steps than a single agent plan alone and preserving execution success. Additionally, we find that LLM-based approximations of subgoals can achieve similar multi-agent execution steps than those specified by human experts. Website and resources at https://glamor-usc.github.io/twostep

ViSaRL: Visual Reinforcement Learning Guided by Human Saliency

Training robots to perform complex control tasks from high-dimensional pixel input using reinforcement learning (RL) is sample-inefficient, because image observations are comprised primarily of task-irrelevant information. By contrast, humans are able to visually attend to task-relevant objects and areas. Based on this insight, we introduce Visual Saliency-Guided Reinforcement Learning (ViSaRL). Using ViSaRL to learn visual representations significantly improves the success rate, sample efficiency, and generalization of an RL agent on diverse tasks including DeepMind Control benchmark, robot manipulation in simulation and on a real robot. We present approaches for incorporating saliency into both CNN and Transformer-based encoders. We show that visual representations learned using ViSaRL are robust to various sources of visual perturbations including perceptual noise and scene variations. ViSaRL nearly doubles success rate on the real-robot tasks compared to the baseline which does not use saliency.

Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning

Prior work on selective prediction minimizes incorrect predictions from vision-language models (VLMs) by allowing them to abstain from answering when uncertain. However, when deploying a vision-language system with low tolerance for inaccurate predictions, selective prediction may be over-cautious and abstain too frequently, even on many correct predictions. We introduce ReCoVERR, an inference-time algorithm to reduce the over-abstention of a selective vision-language system without decreasing prediction accuracy. When the VLM makes a low-confidence prediction, instead of abstaining ReCoVERR tries to find relevant clues in the image that provide additional evidence for the prediction. ReCoVERR uses an LLM to pose related questions to the VLM, collects high-confidence evidences, and if enough evidence confirms the prediction the system makes a prediction instead of abstaining. ReCoVERR enables two VLMs, BLIP2 and InstructBLIP, to answer up to 20% more questions on the A-OKVQA task than vanilla selective prediction without decreasing system accuracy, thus improving overall system reliability.

WinoViz: Probing Visual Properties of Objects Under Different States

Humans perceive and comprehend different visual properties of an object based on specific contexts. For instance, we know that a banana turns brown ``when it becomes rotten,'' whereas it appears green ``when it is unripe.'' Previous studies on probing visual commonsense knowledge have primarily focused on examining language models' understanding of typical properties (e.g., colors and shapes) of objects. We present WinoViz, a text-only evaluation dataset, consisting of 1,380 examples that probe the reasoning abilities of language models regarding variant visual properties of objects under different contexts or states. Our task is challenging since it requires pragmatic reasoning (finding intended meanings) and visual knowledge reasoning. We also present multi-hop data, a more challenging version of our data, which requires multi-step reasoning chains to solve our task. In our experimental analysis, our findings are: a) Large language models such as GPT-4 demonstrate effective performance, but when it comes to multi-hop data, their performance is significantly degraded. b) Large models perform well on pragmatic reasoning, but visual knowledge reasoning is a bottleneck in our task. c) Vision-language models outperform their language-model counterparts. d) A model with machine-generated images performs poorly in our task. This is due to the poor quality of the generated images.