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.

Pre-trained Large Language Models Use Fourier Features to Compute Addition

Pre-trained large language models (LLMs) exhibit impressive mathematical reasoning capabilities, yet how they compute basic arithmetic, such as addition, remains unclear. This paper shows that pre-trained LLMs add numbers using Fourier features -- dimensions in the hidden state that represent numbers via a set of features sparse in the frequency domain. Within the model, MLP and attention layers use Fourier features in complementary ways: MLP layers primarily approximate the magnitude of the answer using low-frequency features, while attention layers primarily perform modular addition (e.g., computing whether the answer is even or odd) using high-frequency features. Pre-training is crucial for this mechanism: models trained from scratch to add numbers only exploit low-frequency features, leading to lower accuracy. Introducing pre-trained token embeddings to a randomly initialized model rescues its performance. Overall, our analysis demonstrates that appropriate pre-trained representations (e.g., Fourier features) can unlock the ability of Transformers to learn precise mechanisms for algorithmic tasks.

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.

IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations

Current foundation models exhibit impressive capabilities when prompted either with text only or with both image and text inputs. But do their capabilities change depending on the input modality? In this work, we propose $\textbf{IsoBench}$, a benchmark dataset containing problems from four major areas: math, science, algorithms, and games. Each example is presented with multiple $\textbf{isomorphic representations}$ of inputs, such as visual, textual, and mathematical presentations. IsoBench provides fine-grained feedback to diagnose performance gaps caused by the form of the representation. Across various foundation models, we observe that on the same problem, models have a consistent preference towards textual representations. Most prominently, when evaluated on all IsoBench problems, Claude-3 Opus performs 28.7 points worse when provided with images instead of text; similarly, GPT-4 Turbo is 18.7 points worse and Gemini Pro is 14.9 points worse. Finally, we present two prompting techniques, $\textit{IsoCombination}$ and $\textit{IsoScratchPad}$, which improve model performance by considering combinations of, and translations between, different input representations.

Proving membership in LLM pretraining data via data watermarks

Detecting whether copyright holders' works were used in LLM pretraining is poised to be an important problem. This work proposes using data watermarks to enable principled detection with only black-box model access, provided that the rightholder contributed multiple training documents and watermarked them before public release. By applying a randomly sampled data watermark, detection can be framed as hypothesis testing, which provides guarantees on the false detection rate. We study two watermarks: one that inserts random sequences, and another that randomly substitutes characters with Unicode lookalikes. We first show how three aspects of watermark design -- watermark length, number of duplications, and interference -- affect the power of the hypothesis test. Next, we study how a watermark's detection strength changes under model and dataset scaling: while increasing the dataset size decreases the strength of the watermark, watermarks remain strong if the model size also increases. Finally, we view SHA hashes as natural watermarks and show that we can robustly detect hashes from BLOOM-176B's training data, as long as they occurred at least 90 times. Together, our results point towards a promising future for data watermarks in real world use.

Does VLN Pretraining Work with Nonsensical or Irrelevant Instructions?

Data augmentation via back-translation is common when pretraining Vision-and-Language Navigation (VLN) models, even though the generated instructions are noisy. But: does that noise matter? We find that nonsensical or irrelevant language instructions during pretraining can have little effect on downstream performance for both HAMT and VLN-BERT on R2R, and is still better than only using clean, human data. To underscore these results, we concoct an efficient augmentation method, Unigram + Object, which generates nonsensical instructions that nonetheless improve downstream performance. Our findings suggest that what matters for VLN R2R pretraining is the quantity of visual trajectories, not the quality of instructions.

Efficient End-to-End Visual Document Understanding with Rationale Distillation

Understanding visually situated language requires recognizing text and visual elements, and interpreting complex layouts. State-of-the-art methods commonly use specialized pre-processing tools, such as optical character recognition (OCR) systems, that map document image inputs to extracted information in the space of textual tokens, and sometimes also employ large language models (LLMs) to reason in text token space. However, the gains from external tools and LLMs come at the cost of increased computational and engineering complexity. In this paper, we ask whether small pretrained image-to-text models can learn selective text or layout recognition and reasoning as an intermediate inference step in an end-to-end model for pixel-level visual language understanding. We incorporate the outputs of such OCR tools, LLMs, and larger multimodal models as intermediate ``rationales'' on training data, and train a small student model to predict both rationales and answers for input questions based on those training examples. A student model based on Pix2Struct (282M parameters) achieves consistent improvements on three visual document understanding benchmarks representing infographics, scanned documents, and figures, with improvements of more than 4\% absolute over a comparable Pix2Struct model that predicts answers directly.

Do Localization Methods Actually Localize Memorized Data in LLMs?

Large language models (LLMs) can memorize many pretrained sequences verbatim. This paper studies if we can locate a small set of neurons in LLMs responsible for memorizing a given sequence. While the concept of localization is often mentioned in prior work, methods for localization have never been systematically and directly evaluated; we address this with two benchmarking approaches. In our INJ Benchmark, we actively inject a piece of new information into a small subset of LLM weights and measure whether localization methods can identify these "ground truth" weights. In the DEL Benchmark, we study localization of pretrained data that LLMs have already memorized; while this setting lacks ground truth, we can still evaluate localization by measuring whether dropping out located neurons erases a memorized sequence from the model. We evaluate five localization methods on our two benchmarks, and both show similar rankings. All methods exhibit promising localization ability, especially for pruning-based methods, though the neurons they identify are not necessarily specific to a single memorized sequence.

Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models

Transformers are remarkably good at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they perform ICL remains a mystery. Recent work suggests that Transformers may learn in-context by internally running Gradient Descent, a first-order optimization method. In this paper, we instead demonstrate that Transformers learn to implement higher-order optimization methods to perform ICL. Focusing on in-context linear regression, we show that Transformers learn to implement an algorithm very similar to Iterative Newton's Method, a higher-order optimization method, rather than Gradient Descent. Empirically, we show that predictions from successive Transformer layers closely match different iterations of Newton's Method linearly, with each middle layer roughly computing 3 iterations. In contrast, exponentially more Gradient Descent steps are needed to match an additional Transformers layer; this suggests that Transformers have an comparable rate of convergence with high-order methods such as Iterative Newton, which are exponentially faster than Gradient Descent. We also show that Transformers can learn in-context on ill-conditioned data, a setting where Gradient Descent struggles but Iterative Newton succeeds. Finally, we show theoretical results which support our empirical findings and have a close correspondence with them: we prove that Transformers can implement $k$ iterations of Newton's method with $\mathcal{O}(k)$ layers.

Estimating Large Language Model Capabilities without Labeled Test Data

Large Language Models (LLMs) have exhibited an impressive ability to perform in-context learning (ICL) from only a few examples, but the success of ICL varies widely from task to task. Thus, it is important to quickly determine whether ICL is applicable to a new task, but directly evaluating ICL accuracy can be expensive in situations where test data is expensive to annotate -- the exact situations where ICL is most appealing. In this paper, we propose the task of ICL accuracy estimation, in which we predict the accuracy of an LLM when doing in-context learning on a new task given only unlabeled data for that task. To perform ICL accuracy estimation, we propose a method that trains a meta-model using LLM confidence scores as features. We compare our method to several strong accuracy estimation baselines on a new benchmark that covers 4 LLMs and 3 task collections. On average, the meta-model improves over all baselines and achieves the same estimation performance as directly evaluating on 40 labeled test examples per task, across the total 12 settings. We encourage future work to improve on our methods and evaluate on our ICL accuracy estimation benchmark to deepen our understanding of when ICL works.