Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions

Large language models (LLMs) such as ChatGPT and GPT-4 have recently demonstrated their remarkable abilities of communicating with human users. In this technical report, we take an initiative to investigate their capacities of playing text games, in which a player has to understand the environment and respond to situations by having dialogues with the game world. Our experiments show that ChatGPT performs competitively compared to all the existing systems but still exhibits a low level of intelligence. Precisely, ChatGPT can not construct the world model by playing the game or even reading the game manual; it may fail to leverage the world knowledge that it already has; it cannot infer the goal of each step as the game progresses. Our results open up new research questions at the intersection of artificial intelligence, machine learning, and natural language processing.

Explicit Planning Helps Language Models in Logical Reasoning

Language models have been shown to perform remarkably well on a wide range of natural language processing tasks. In this paper, we propose a novel system that uses language models to perform multi-step logical reasoning. Our system incorporates explicit planning into its inference procedure, thus able to make more informed reasoning decisions at each step by looking ahead into their future effects. In our experiments, our full system significantly outperforms other competing systems. On a multiple-choice question answering task, our system performs competitively compared to GPT-3-davinci despite having only around 1.5B parameters. We conduct several ablation studies to demonstrate that explicit planning plays a crucial role in the system's performance.

MetaNO: How to Transfer Your Knowledge on Learning Hidden Physics

Gradient-based meta-learning methods have primarily been applied to classical machine learning tasks such as image classification. Recently, PDE-solving deep learning methods, such as neural operators, are starting to make an important impact on learning and predicting the response of a complex physical system directly from observational data. Since the data acquisition in this context is commonly challenging and costly, the call of utilization and transfer of existing knowledge to new and unseen physical systems is even more acute. Herein, we propose a novel meta-learning approach for neural operators, which can be seen as transferring the knowledge of solution operators between governing (unknown) PDEs with varying parameter fields. Our approach is a provably universal solution operator for multiple PDE solving tasks, with a key theoretical observation that underlying parameter fields can be captured in the first layer of neural operator models, in contrast to typical final-layer transfer in existing meta-learning methods. As applications, we demonstrate the efficacy of our proposed approach on PDE-based datasets and a real-world material modeling problem, illustrating that our method can handle complex and nonlinear physical response learning tasks while greatly improving the sampling efficiency in unseen tasks.

Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind

When reading a story, humans can rapidly understand new fictional characters with a few observations, mainly by drawing analogy to fictional and real people they met before in their lives. This reflects the few-shot and meta-learning essence of humans' inference of characters' mental states, i.e., humans' theory-of-mind (ToM), which is largely ignored in existing research. We fill this gap with a novel NLP benchmark, TOM-IN-AMC, the first assessment of models' ability of meta-learning of ToM in a realistic narrative understanding scenario. Our benchmark consists of $\sim$1,000 parsed movie scripts for this purpose, each corresponding to a few-shot character understanding task; and requires models to mimic humans' ability of fast digesting characters with a few starting scenes in a new movie. Our human study verified that humans can solve our problem by inferring characters' mental states based on their previously seen movies; while the state-of-the-art metric-learning and meta-learning approaches adapted to our task lags 30% behind.

Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension

In this work, we focus on dialogue reading comprehension (DRC), a task extracting answer spans for questions from dialogues. Dialogue context modeling in DRC is tricky due to complex speaker information and noisy dialogue context. To solve the two problems, previous research proposes two self-supervised tasks respectively: guessing who a randomly masked speaker is according to the dialogue and predicting which utterance in the dialogue contains the answer. Although these tasks are effective, there are still urging problems: (1) randomly masking speakers regardless of the question cannot map the speaker mentioned in the question to the corresponding speaker in the dialogue, and ignores the speaker-centric nature of utterances. This leads to wrong answer extraction from utterances in unrelated interlocutors' scopes; (2) the single utterance prediction, preferring utterances similar to the question, is limited in finding answer-contained utterances not similar to the question. To alleviate these problems, we first propose a new key utterances extracting method. It performs prediction on the unit formed by several contiguous utterances, which can realize more answer-contained utterances. Based on utterances in the extracted units, we then propose Question-Interlocutor Scope Realized Graph (QuISG) modeling. As a graph constructed on the text of utterances, QuISG additionally involves the question and question-mentioning speaker names as nodes. To realize interlocutor scopes, speakers in the dialogue are connected with the words in their corresponding utterances. Experiments on the benchmarks show that our method can achieve better and competitive results against previous works.

Revisiting the Roles of "Text" in Text Games

Text games present opportunities for natural language understanding (NLU) methods to tackle reinforcement learning (RL) challenges. However, recent work has questioned the necessity of NLU by showing random text hashes could perform decently. In this paper, we pursue a fine-grained investigation into the roles of text in the face of different RL challenges, and reconcile that semantic and non-semantic language representations could be complementary rather than contrasting. Concretely, we propose a simple scheme to extract relevant contextual information into an approximate state hash as extra input for an RNN-based text agent. Such a lightweight plug-in achieves competitive performance with state-of-the-art text agents using advanced NLU techniques such as knowledge graph and passage retrieval, suggesting non-NLU methods might suffice to tackle the challenge of partial observability. However, if we remove RNN encoders and use approximate or even ground-truth state hash alone, the model performs miserably, which confirms the importance of semantic function approximation to tackle the challenge of combinatorially large observation and action spaces. Our findings and analysis provide new insights for designing better text game task setups and agents.

Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information-acquisition-oriented dialogue system employs a novel adaptation of reinforced self-play so that the system can be transferred to various domains without in-domain dialogue data, and can carry out conversations both informative and attentive to users. Our extensive subjective and objective evaluations on three large public data corpora demonstrate the effectiveness of our system to deliver knowledge-intensive and attentive conversations and help end users substantially gain knowledge without reading passages. Our code and datasets are publicly available for follow-up research.

A Survey of Machine Narrative Reading Comprehension Assessments

As the body of research on machine narrative comprehension grows, there is a critical need for consideration of performance assessment strategies as well as the depth and scope of different benchmark tasks. Based on narrative theories, reading comprehension theories, as well as existing machine narrative reading comprehension tasks and datasets, we propose a typology that captures the main similarities and differences among assessment tasks; and discuss the implications of our typology for new task design and the challenges of narrative reading comprehension.

FaithDial: A Faithful Benchmark for Information-Seeking Dialogue

The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources. However, dialogue systems often produce unsupported utterances, a phenomenon known as hallucination. Dziri et al. (2022)'s investigation of hallucinations has revealed that existing knowledge-grounded benchmarks are contaminated with hallucinated responses at an alarming level (>60% of the responses) and models trained on this data amplify hallucinations even further (>80% of the responses). To mitigate this behavior, we adopt a data-centric solution and create FaithDial, a new benchmark for hallucination-free dialogues, by editing hallucinated responses in the Wizard of Wikipedia (WoW) benchmark. We observe that FaithDial is more faithful than WoW while also maintaining engaging conversations. We show that FaithDial can serve as a training signal for: i) a hallucination critic, which discriminates whether an utterance is faithful or not, and boosts the performance by 21.1 F1 score on the BEGIN benchmark compared to existing datasets for dialogue coherence; ii) high-quality dialogue generation. We benchmark a series of state-of-the-art models and propose an auxiliary contrastive objective that achieves the highest level of faithfulness and abstractiveness based on several automated metrics. Further, we find that the benefits of FaithDial generalize to zero-shot transfer on other datasets, such as CMU-Dog and TopicalChat. Finally, human evaluation reveals that responses generated by models trained on FaithDial are perceived as more interpretable, cooperative, and engaging.