Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills. Are these skills general and transferable, or specialized to specific tasks seen during pretraining? To disentangle these effects, we propose an evaluation framework based on "counterfactual" task variants that deviate from the default assumptions underlying standard tasks. Across a suite of 11 tasks, we observe nontrivial performance on the counterfactual variants, but nevertheless find that performance substantially and consistently degrades compared to the default conditions. This suggests that while current LMs may possess abstract task-solving skills to a degree, they often also rely on narrow, non-transferable procedures for task-solving. These results motivate a more careful interpretation of language model performance that teases apart these aspects of behavior.

Inverse Scaling: When Bigger Isn't Better

Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, we present evidence for the claim that LMs may show inverse scaling, or worse task performance with increased scale, e.g., due to flaws in the training objective and data. We present empirical evidence of inverse scaling on 11 datasets collected by running a public contest, the Inverse Scaling Prize, with a substantial prize pool. Through analysis of the datasets, along with other examples found in the literature, we identify four potential causes of inverse scaling: (i) preference to repeat memorized sequences over following in-context instructions, (ii) imitation of undesirable patterns in the training data, (iii) tasks containing an easy distractor task which LMs could focus on, rather than the harder real task, and (iv) correct but misleading few-shot demonstrations of the task. We release the winning datasets at https://inversescaling.com/data to allow for further investigation of inverse scaling. Our tasks have helped drive the discovery of U-shaped and inverted-U scaling trends, where an initial trend reverses, suggesting that scaling trends are less reliable at predicting the behavior of larger-scale models than previously understood. Overall, our results suggest that there are tasks for which increased model scale alone may not lead to progress, and that more careful thought needs to go into the data and objectives for training language models.

BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information

Automated reasoning with unstructured natural text is a key requirement for many potential applications of NLP and for developing robust AI systems. Recently, Language Models (LMs) have demonstrated complex reasoning capacities even without any finetuning. However, existing evaluation for automated reasoning assumes access to a consistent and coherent set of information over which models reason. When reasoning in the real-world, the available information is frequently inconsistent or contradictory, and therefore models need to be equipped with a strategy to resolve such conflicts when they arise. One widely-applicable way of resolving conflicts is to impose preferences over information sources (e.g., based on source credibility or information recency) and adopt the source with higher preference. In this paper, we formulate the problem of reasoning with contradictory information guided by preferences over sources as the classical problem of defeasible reasoning, and develop a dataset called BoardgameQA for measuring the reasoning capacity of LMs in this setting. BoardgameQA also incorporates reasoning with implicit background knowledge, to better reflect reasoning problems in downstream applications. We benchmark various LMs on BoardgameQA and the results reveal a significant gap in the reasoning capacity of state-of-the-art LMs on this problem, showing that reasoning with conflicting information does not surface out-of-the-box in LMs. While performance can be improved with finetuning, it nevertheless remains poor.

Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples

Given the intractably large size of the space of proofs, any model that is capable of general deductive reasoning must generalize to proofs of greater complexity. Recent studies have shown that large language models (LLMs) possess some abstract deductive reasoning ability given chain-of-thought prompts. However, they have primarily been tested on proofs using modus ponens or of a specific size, and from the same distribution as the in-context examples. To measure the general deductive reasoning ability of LLMs, we test on a broad set of deduction rules and measure their ability to generalize to more complex proofs from simpler demonstrations from multiple angles: depth-, width-, and compositional generalization. To facilitate systematic exploration, we construct a new synthetic and programmable reasoning dataset that enables control over deduction rules and proof complexity. Our experiments on four LLMs of various sizes and training objectives show that they are able to generalize to longer and compositional proofs. However, they require explicit demonstrations to produce hypothetical subproofs, specifically in proof by cases and proof by contradiction.

Entity Tracking in Language Models

Keeping track of how states and relations of entities change as a text or dialog unfolds is a key prerequisite to discourse understanding. Despite this fact, there have been few systematic investigations into the ability of large language models (LLMs) to track discourse entities. In this work, we present a task to probe to what extent a language model can infer the final state of an entity given an English description of the initial state and a series of state-changing operations. We use this task to first investigate whether Flan-T5, GPT-3 and GPT-3.5 can track the state of entities, and find that only GPT-3.5 models, which have been pretrained on large amounts of code, exhibit this ability. We then investigate whether smaller models pretrained primarily on text can learn to track entities, through finetuning T5 on several training/evaluation splits. While performance degrades for more complex splits, we find that even for splits with almost no lexical overlap between training and evaluation, a finetuned model can often perform non-trivial entity tracking. Taken together, these results suggest that language models can learn to track entities but pretraining on large text corpora alone does not make this capacity surface.

Reconstruction Probing

We propose reconstruction probing, a new analysis method for contextualized representations based on reconstruction probabilities in masked language models (MLMs). This method relies on comparing the reconstruction probabilities of tokens in a given sequence when conditioned on the representation of a single token that has been fully contextualized and when conditioned on only the decontextualized lexical prior of the model. This comparison can be understood as quantifying the contribution of contextualization towards reconstruction -- the difference in the reconstruction probabilities can only be attributed to the representational change of the single token induced by contextualization. We apply this analysis to three MLMs and find that contextualization boosts reconstructability of tokens that are close to the token being reconstructed in terms of linear and syntactic distance. Furthermore, we extend our analysis to finer-grained decomposition of contextualized representations, and we find that these boosts are largely attributable to static and positional embeddings at the input layer.

Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models

Human linguistic capacity is often characterized by compositionality and the generalization it enables -- human learners can produce and comprehend novel complex expressions by composing known parts. Several benchmarks exploit distributional control across training and test to gauge compositional generalization, where certain lexical items only occur in limited contexts during training. While recent work using these benchmarks suggests that pretrained models achieve impressive generalization performance, we argue that exposure to pretraining data may break the aforementioned distributional control. Using the COGS benchmark of Kim and Linzen (2020), we test two modified evaluation setups that control for this issue: (1) substituting context-controlled lexical items with novel character sequences, and (2) substituting them with special tokens represented by novel embeddings. We find that both of these setups lead to lower generalization performance in T5 (Raffel et al., 2020), suggesting that previously reported results have been overestimated due to uncontrolled lexical exposure during pretraining. The performance degradation is more extreme with novel embeddings, and the degradation increases with the amount of pretraining data, highlighting an interesting case of inverse scaling.

LAMBADA: Backward Chaining for Automated Reasoning in Natural Language

Remarkable progress has been made on automated reasoning with knowledge specified as unstructured, natural text, by using the power of large language models (LMs) coupled with methods such as Chain-of-Thought prompting and Selection-Inference. These techniques search for proofs in the forward direction from axioms to the conclusion, which suffers from a combinatorial explosion of the search space, and thus high failure rates for problems requiring longer chains of reasoning. The classical automated reasoning literature has shown that reasoning in the backward direction (i.e. from the intended conclusion to the set of axioms that support it) is significantly more efficient at proof-finding problems. We import this intuition into the LM setting and develop a Backward Chaining algorithm, which we call LAMBADA, that decomposes reasoning into four sub-modules, each of which can be simply implemented by few-shot prompted LM inference. We show that LAMBADA achieves massive accuracy boosts over state-of-the-art forward reasoning methods on two challenging logical reasoning datasets, particularly when deep and accurate proof chains are required.

(QA)$^2$: Question Answering with Questionable Assumptions

Naturally-occurring information-seeking questions often contain questionable assumptions -- assumptions that are false or unverifiable. Questions containing questionable assumptions are challenging because they require a distinct answer strategy that deviates from typical answers to information-seeking questions. For instance, the question "When did Marie Curie discover Uranium?" cannot be answered as a typical when question without addressing the false assumption "Marie Curie discovered Uranium". In this work, we propose (QA)$^2$ (Question Answering with Questionable Assumptions), an open-domain evaluation dataset consisting of naturally-occurring search engine queries that may or may not contain questionable assumptions. To be successful on (QA)$^2$, systems must be able to detect questionable assumptions and also be able to produce adequate responses for both typical information-seeking questions and ones with questionable assumptions. We find that current models do struggle with handling questionable assumptions -- the best performing model achieves 59% human rater acceptability on abstractive QA with (QA)$^2$ questions, leaving substantial headroom for progress.