We introduce the dataset of Everyday Hard Optimization Problems (EHOP), a collection of NP-hard optimization problems expressed in natural language. EHOP includes problem formulations that could be found in computer science textbooks, versions that are dressed up as problems that could arise in real life, and variants of well-known problems with inverted rules. We find that state-of-the-art LLMs, across multiple prompting strategies, systematically solve textbook problems more accurately than their real-life and inverted counterparts. We argue that this constitutes evidence that LLMs adapt solutions seen during training, rather than leveraging reasoning abilities that would enable them to generalize to novel problems.

An increasingly common practice is to train large language models (LLMs) using synthetic data. Often this synthetic data is produced by the same or similar LLMs as those it is being used to train. This raises the question of whether the synthetic data might in fact exacerbate certain "blindspots" by reinforcing heuristics that the LLM already encodes. In this paper, we conduct simulated experiments on the natural language inference (NLI) task with Llama-2-7B-hf models. We use MultiNLI as the general task and HANS, a targeted evaluation set designed to measure the presence of specific heuristic strategies for NLI, as our "blindspot" task. Our goal is to determine whether performance disparities between the general and blind spot tasks emerge. Our results indicate that synthetic data does not reinforce blindspots in the way we expected. Specifically, we see that, while fine-tuning with synthetic data doesn't necessarily reduce the use of the heuristic, it also does not make it worse as we hypothesized.

Pre-training is notoriously compute-intensive and academic researchers are notoriously under-resourced. It is, therefore, commonly assumed that academics can't pre-train models. In this paper, we seek to clarify this assumption. We first survey academic researchers to learn about their available compute and then empirically measure the time to replicate models on such resources. We introduce a benchmark to measure the time to pre-train models on given GPUs and also identify ideal settings for maximizing training speed. We run our benchmark on a range of models and academic GPUs, spending 2,000 GPU-hours on our experiments. Our results reveal a brighter picture for academic pre-training: for example, although Pythia-1B was originally trained on 64 GPUs for 3 days, we find it is also possible to replicate this model (with the same hyper-parameters) in 3x fewer GPU-days: i.e. on 4 GPUs in 18 days. We conclude with a cost-benefit analysis to help clarify the trade-offs between price and pre-training time. We believe our benchmark will help academic researchers conduct experiments that require training larger models on more data. We fully release our codebase at: https://github.com/apoorvkh/academic-pretraining.

Distributional semantics is the linguistic theory that a word's meaning can be derived from its distribution in natural language (i.e., its use). Language models are commonly viewed as an implementation of distributional semantics, as they are optimized to capture the statistical features of natural language. It is often argued that distributional semantics models should excel at capturing graded/vague meaning based on linguistic conventions, but struggle with truth-conditional reasoning and symbolic processing. We evaluate this claim with a case study on vague (e.g. "many") and exact (e.g. "more than half") quantifiers. Contrary to expectations, we find that, across a broad range of models of various types, LLMs align more closely with human judgements on exact quantifiers versus vague ones. These findings call for a re-evaluation of the assumptions underpinning what distributional semantics models are, as well as what they can capture.

Using English and Chinese multilingual and monolingual models, we analyze the internal circuitry involved in two tasks, one focusing on indirect object identification (IOI) which is virtually identical between the languages, and one which involves generating paste tense verbs that require morphological marking in English but not in Chinese. Our contributions are as follows: We show that a multilingual model uses a single circuit to handle the same syntactic process independently of the language in which it occurs ( 3.4). We show that even monolingual models trained independently on English and Chinese each adopt nearly the same circuit for this task ( 3.5), suggesting a surprising amount of consistency with how LLMs learn to handle this particular aspect of language modeling. Finally, we show that, when faced with similar tasks that require language-specific morphological processes, multilingual models still invoke a largely overlapping circuit, but employ language-specific components as needed. Specifically, in our task, we find that the model uses a circuit that consists primarily of attention heads to perform most of the task, but employs the feed-forward networks in English only to perform morphological marking that is necessary in English but not in Chinese ( 4). Together, our results provide new insights into how LLMs trade off between exploiting common structures and preserving linguistic differences when tasked with modeling multiple languages simultaneously. Our experiments can lay the groundwork for future works which seek to improve cross-lingual transfer through more principled parameter updates (Wu et al., 2024), as well as work which seeks to use LLMs in order to improve the study of linguistic and grammatical structure for its own sake (Lakretz et al., 2021; Misra & Kim, 2024).

Language models have the ability to perform in-context learning (ICL), allowing them to flexibly adapt their behavior based on context. This contrasts with in-weights learning, where information is statically encoded in model parameters from iterated observations of the data. Despite this apparent ability to learn in-context, language models are known to struggle when faced with unseen or rarely seen tokens. Hence, we study $\textbf{structural in-context learning}$, which we define as the ability of a model to execute in-context learning on arbitrary tokens -- so called because the model must generalize on the basis of e.g. sentence structure or task structure, rather than semantic content encoded in token embeddings. An ideal model would be able to do both: flexibly deploy in-weights operations (in order to robustly accommodate ambiguous or unknown contexts using encoded semantic information) and structural in-context operations (in order to accommodate novel tokens). We study structural in-context algorithms in a simple part-of-speech setting using both practical and toy models. We find that active forgetting, a technique that was recently introduced to help models generalize to new languages, forces models to adopt structural in-context learning solutions. Finally, we introduce $\textbf{temporary forgetting}$, a straightforward extension of active forgetting that enables one to control how much a model relies on in-weights vs. in-context solutions. Importantly, temporary forgetting allows us to induce a $\textit{dual process strategy}$ where in-context and in-weights solutions coexist within a single model.

Analogical reasoning is considered core to human learning and cognition. Recent studies have compared the analogical reasoning abilities of human subjects and Large Language Models (LLMs) on abstract symbol manipulation tasks, such as letter string analogies. However, these studies largely neglect analogical reasoning over semantically meaningful symbols, such as natural language words. This ability to draw analogies that link language to non-linguistic domains, which we term semantic structure-mapping, is thought to play a crucial role in language acquisition and broader cognitive development. We test human subjects and LLMs on analogical reasoning tasks that require the transfer of semantic structure and content from one domain to another. Advanced LLMs match human performance across many task variations. However, humans and LLMs respond differently to certain task variations and semantic distractors. Overall, our data suggest that LLMs are approaching human-level performance on these important cognitive tasks, but are not yet entirely human like.

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. By analyzing particular mechanism LMs use to accomplish this, we find that it is also used to recall items from a list, and show that this mechanism can explain an otherwise arbitrary-seeming sensitivity of the model to the order of items in the prompt. Specifically, we find that models write into low-rank subspaces of the residual stream to represent features which are then read out by specific later layers, forming low-rank communication channels between layers. By decomposing attention head weight matrices with the Singular Value Decomposition (SVD), we find that previously described interactions between heads separated by one or more layers can be predicted via analysis of their weight matrices. We show that it is possible to manipulate the internal model representations as well as edit model weights based on the mechanism we discover in order to significantly improve performance on our synthetic Laundry List task, which requires recall from a list, often improving task accuracy by over 20%. Our analysis reveals a surprisingly intricate interpretable structure learned from language model pretraining, and helps us understand why sophisticated LMs sometimes fail in simple domains, facilitating future analysis of more complex behaviors.

Effective evaluation of language models remains an open challenge in NLP. Researchers and engineers face methodological issues such as the sensitivity of models to evaluation setup, difficulty of proper comparisons across methods, and the lack of reproducibility and transparency. In this paper we draw on three years of experience in evaluating large language models to provide guidance and lessons for researchers. First, we provide an overview of common challenges faced in language model evaluation. Second, we delineate best practices for addressing or lessening the impact of these challenges on research. Third, we present the Language Model Evaluation Harness (lm-eval): an open source library for independent, reproducible, and extensible evaluation of language models that seeks to address these issues. We describe the features of the library as well as case studies in which the library has been used to alleviate these methodological concerns.

Many pretrained multilingual models exhibit cross-lingual transfer ability, which is often attributed to a learned language-neutral representation during pretraining. However, it remains unclear what factors contribute to the learning of a language-neutral representation, and whether the learned language-neutral representation suffices to facilitate cross-lingual transfer. We propose a synthetic task, Multilingual Othello (mOthello), as a testbed to delve into these two questions. We find that: (1) models trained with naive multilingual pretraining fail to learn a language-neutral representation across all input languages; (2) the introduction of "anchor tokens" (i.e., lexical items that are identical across languages) helps cross-lingual representation alignment; and (3) the learning of a language-neutral representation alone is not sufficient to facilitate cross-lingual transfer. Based on our findings, we propose a novel approach - multilingual pretraining with unified output space - that both induces the learning of language-neutral representation and facilitates cross-lingual transfer.