The commercialization of large language models (LLMs) has led to the common practice of high-level API-only access to proprietary models. In this work, we show that even with a conservative assumption about the model architecture, it is possible to learn a surprisingly large amount of non-public information about an API-protected LLM from a relatively small number of API queries (e.g., costing under $1,000 for OpenAI's gpt-3.5-turbo). Our findings are centered on one key observation: most modern LLMs suffer from a softmax bottleneck, which restricts the model outputs to a linear subspace of the full output space. We show that this lends itself to a model image or a model signature which unlocks several capabilities with affordable cost: efficiently discovering the LLM's hidden size, obtaining full-vocabulary outputs, detecting and disambiguating different model updates, identifying the source LLM given a single full LLM output, and even estimating the output layer parameters. Our empirical investigations show the effectiveness of our methods, which allow us to estimate the embedding size of OpenAI's gpt-3.5-turbo to be about 4,096. Lastly, we discuss ways that LLM providers can guard against these attacks, as well as how these capabilities can be viewed as a feature (rather than a bug) by allowing for greater transparency and accountability.
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.
Large language models (LLMs) have achieved impressive human-like performance across various reasoning tasks. However, their mastery of underlying inferential rules still falls short of human capabilities. To investigate this, we propose a logic scaffolding inferential rule generation framework, to construct an inferential rule base, ULogic, comprising both primitive and compositional rules across five domains. Our analysis of GPT-series models over a rule subset reveals significant gaps in LLMs' logic understanding compared to human performance, especially in compositional and structural complex rules with certain bias patterns. We further distill these rules into a smaller-scale inference engine for flexible rule generation and enhancing downstream reasoning. Through a multi-judger evaluation, our inference engine proves effective in generating accurate, complex and abstract conclusions and premises, and improve various commonsense reasoning tasks. Overall, our work sheds light on LLMs' limitations in grasping inferential rule and suggests ways to enhance their logical reasoning abilities~\footnote{Code and data are available at \url{https://github.com/SiyuanWangw/ULogic}.}.
Humans make numerous inferences in text comprehension to understand discourse. This paper aims to understand the commonalities and disparities in the inference judgments between humans and state-of-the-art Large Language Models (LLMs). Leveraging a comprehensively curated entailment verification benchmark, we evaluate both human and LLM performance across various reasoning categories. Our benchmark includes datasets from three categories (NLI, contextual QA, and rationales) that include multi-sentence premises and different knowledge types, thereby evaluating the inference capabilities in complex reasoning instances. Notably, our findings reveal LLMs' superiority in multi-hop reasoning across extended contexts, while humans excel in tasks necessitating simple deductive reasoning. Leveraging these insights, we introduce a fine-tuned Flan-T5 model that outperforms GPT-3.5 and rivals with GPT-4, offering a robust open-source solution for entailment verification. As a practical application, we showcase the efficacy of our finetuned model in enhancing self-consistency in model-generated explanations, resulting in a 6% performance boost on average across three multiple-choice question-answering datasets.
We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods. Core to the framework is a self-discovery process where LLMs select multiple atomic reasoning modules such as critical thinking and step-by-step thinking, and compose them into an explicit reasoning structure for LLMs to follow during decoding. SELF-DISCOVER substantially improves GPT-4 and PaLM 2's performance on challenging reasoning benchmarks such as BigBench-Hard, grounded agent reasoning, and MATH, by as much as 32% compared to Chain of Thought (CoT). Furthermore, SELF-DISCOVER outperforms inference-intensive methods such as CoT-Self-Consistency by more than 20%, while requiring 10-40x fewer inference compute. Finally, we show that the self-discovered reasoning structures are universally applicable across model families: from PaLM 2-L to GPT-4, and from GPT-4 to Llama2, and share commonalities with human reasoning patterns.
Language models deployed in the wild make errors. However, simply updating the model with the corrected error instances causes catastrophic forgetting -- the updated model makes errors on instances learned during the instruction tuning or upstream training phase. Randomly replaying upstream data yields unsatisfactory performance and often comes with high variance and poor controllability. To this end, we try to forecast upstream examples that will be forgotten due to a model update for improved controllability of the replay process and interpretability. We train forecasting models given a collection of online learned examples and corresponding forgotten upstream pre-training examples. We propose a partially interpretable forecasting model based on the observation that changes in pre-softmax logit scores of pretraining examples resemble that of online learned examples, which performs decently on BART but fails on T5 models. We further show a black-box classifier based on inner products of example representations achieves better forecasting performance over a series of setups. Finally, we show that we reduce forgetting of upstream pretraining examples by replaying examples that are forecasted to be forgotten, demonstrating the practical utility of forecasting example forgetting.
As natural language becomes the default interface for human-AI interaction, there is a critical need for LMs to appropriately communicate uncertainties in downstream applications. In this work, we investigate how LMs incorporate confidence about their responses via natural language and how downstream users behave in response to LM-articulated uncertainties. We examine publicly deployed models and find that LMs are unable to express uncertainties when answering questions even when they produce incorrect responses. LMs can be explicitly prompted to express confidences, but tend to be overconfident, resulting in high error rates (on average 47%) among confident responses. We test the risks of LM overconfidence by running human experiments and show that users rely heavily on LM generations, whether or not they are marked by certainty. Lastly, we investigate the preference-annotated datasets used in RLHF alignment and find that humans have a bias against texts with uncertainty. Our work highlights a new set of safety harms facing human-LM interactions and proposes design recommendations and mitigating strategies moving forward.
This paper explores the potential wireless communication applications of Reconfigurable Intelligent Surfaces (RIS) in reverberant wave propagation environments. Unlike in free space, we utilize the sensitivity to boundaries of the enclosed electromagnetic (EM) field and the equivalent perturbation of RISs. For the first time, we introduce the framework of reconfigurable boundary modulation in the cavities . We have proposed a robust boundary modulation scheme that exploits the continuity of object motion and the mutation of the codebook switch, which achieves pulse position modulation (PPM) by RIS-generated equivalent pulses for wireless communication in cavities. This approach achieves around 2 Mbps bit rate in the prototype and demonstrates strong resistance to channel's frequency selectivity resulting in an extremely low bit error rate (BER).
Since large language models have approached human-level performance on many tasks, it has become increasingly harder for researchers to find tasks that are still challenging to the models. Failure cases usually come from the long-tail distribution - data that an oracle language model could assign a probability on the lower end of its distribution. Current methodology such as prompt engineering or crowdsourcing are insufficient for creating long-tail examples because humans are constrained by cognitive bias. We propose a Logic-Induced-Knowledge-Search (LINK) framework for systematically generating long-tail knowledge statements. Grounded by a symbolic rule, we search for long-tail values for each variable of the rule by first prompting a LLM, then verifying the correctness of the values with a critic, and lastly pushing for the long-tail distribution with a reranker. With this framework we construct a dataset, Logic-Induced-Long-Tail (LINT), consisting of 200 symbolic rules and 50K knowledge statements spanning across four domains. Human annotations find that 84% of the statements in LINT are factually correct. In contrast, ChatGPT and GPT4 struggle with directly generating long-tail statements under the guidance of logic rules, each only getting 56% and 78% of their statements correct. Moreover, their "long-tail" generations in fact fall into the higher likelihood range, and thus are not really long-tail. Our findings suggest that LINK is effective for generating data in the long-tail distribution while enforcing quality. LINT can be useful for systematically evaluating LLMs' capabilities in the long-tail distribution. We challenge the models with a simple entailment classification task using samples from LINT. We find that ChatGPT and GPT4's capability in identifying incorrect knowledge drop by ~3% in the long-tail distribution compared to head distribution.
Large language models (LMs) are capable of generating free-text rationales to aid question answering. However, prior work 1) suggests that useful self-rationalization is emergent only at significant scales (e.g., 175B parameter GPT-3); and 2) focuses largely on downstream performance, ignoring the semantics of the rationales themselves, e.g., are they faithful, true, and helpful for humans? In this work, we enable small-scale LMs (approx. 200x smaller than GPT-3) to generate rationales that not only improve downstream task performance, but are also more plausible, consistent, and diverse, assessed both by automatic and human evaluation. Our method, MaRio (Multi-rewArd RatIOnalization), is a multi-reward conditioned self-rationalization algorithm that optimizes multiple distinct properties like plausibility, diversity and consistency. Results on five difficult question-answering datasets StrategyQA, QuaRel, OpenBookQA, NumerSense and QASC show that not only does MaRio improve task accuracy, but it also improves the self-rationalization quality of small LMs across the aforementioned axes better than a supervised fine-tuning (SFT) baseline. Extensive human evaluations confirm that MaRio rationales are preferred vs. SFT rationales, as well as qualitative improvements in plausibility and consistency.