44 accepted papers
Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increasingly high-stakes. Fortunately, advances in alignment have significantly reduced the likelihood of harmful model outputs. However, when models are qu…
Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's chain-of-thought (CoT), or implicit, where the CoT appears benign thus…
Jailbreak transferability is the surprising phenomenon when an adversarial attack compromising one model also elicits harmful responses from other models. Despite widespread demonstrations, there is little consensus on why transfer is possible: is it a quirk of safety training, an artifact of model…
As large language models (LLMs) are increasingly used for ideation and scientific discovery, it is important to evaluate their ability to generate novel output. Prior work evaluates novelty as originality with respect to model training data, but original outputs can be of low quality. In contrast, n…
As LLMs become more agentic, a critical risk emerges: attackers can \emph{decompose} harmful goals into stateful, benign subtasks that trick LLM agents into executing them without realizing the harmful intent in the same context. The challenge lies in the existing shallow safety alignment techniques…
Instruction following in LLMs captures models' ability to change their visible behaviors as requested by users. Instead, we study models' ability to control their chain-of-thought (CoT). This capability -- CoT controllability -- is undesirable because it could allow models to suppress signs of misbe…
Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language Model's (LLM) reasoning ability. However, the learning dynamics of RLVR remain underexplored. In this paper, we reveal a curious phenomenon: among hard examples that the model initially struggles wi…
As large language models (LLMs) grow more powerful, they also become more difficult to trust. They could be either aligned with human intentions, or exhibit "subversive misalignment" -- introducing subtle errors that bypass safety checks. Although individual errors may not immediately cause harm, ea…
Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this problem: to achieve higher rewards, LMs might get better at convincing humans that they are right even when they are wron…
Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even expert researchers can only acquire through substantial experi…
Large language models (LLMs) often generate convincing, fluent explanations. However, different from humans, they often generate inconsistent explanations on different inputs. For example, an LLM may explain “all birds can fly” when answering the question “Can sparrows fly?” but meanwhile answer “no…
Search is an ability foundational in many important tasks, and recent studies have shown that large language models (LLMs) struggle to perform search robustly. It is unknown whether this inability is due to a lack of data, insufficient model parameters, or fundamental limitations of the transformer…
Programming with a coding assistant is a fundamentally interactive process, yet existing static benchmarks fail to capture key features of model-user collaboration. We introduce an interactive evaluation pipeline to examine how LLMs incorporate different types of feedback in a collaborative setting,…
Large language models (LLMs) are trained to imitate humans to explain human decisions. However, do LLMs explain themselves? Can they help humans build mental models of how LLMs process different inputs? To answer these questions, we propose to evaluate $\textbf{counterfactual simulatability}$ of nat…
Large language models (LLMs) have led to a surge in collaborative writing with model assistance. As different users incorporate suggestions from the same model, there is a risk of decreased diversity in the produced content, potentially limiting diverse perspectives in public discourse. In this work…
Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks. In this work we develop an iterative approach that optimizes the preference between competing generated Chain-of-Thought…
Recent work shows that causal facts can be effectively extracted from LLMs through prompting, facilitating the creation of causal graphs for causal inference tasks. However, it is unclear if this success is limited to explicitly-mentioned causal facts in the pretraining data which the model can memo…
Pre-trained language models (LMs) are capable of in-context learning (ICL): they can adapt to a task with only a few examples given in the prompt without any parameter update. However, it is unclear where this capability comes from as there is a stark distribution shift between pre-training text and…
Large language models (LLMs) are trained on vast amounts of text from the internet, which contains both factual and misleading information about the world. While unintuitive from a classic view of LMs, recent work has shown that the truth value of a statement can be elicited from the model’s represe…
The choice of hyperparameters greatly impacts performance in natural language processing. Often, it is hard to tell if a method is better than another or just better tuned. *Tuning curves* fix this ambiguity by accounting for tuning effort. Specifically, they plot validation performance as a functio…
Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about the methods (how), domains (where), people (who) and objectives (to what end) of feedback processes. To navigate these questions, we introduce PRISM, a new dataset which maps the sociodem…
Language agents that interact with the world on their own have great potential for automating digital tasks. While large language model (LLM) agents have made progress in understanding and executing tasks such as textual games and webpage control, many real-world tasks also require collaboration wit…
Despite the popularity of Shapley Values in explaining neural text classification models, computing them is prohibitive for large pretrained models due to a large number of model evaluations. In practice, Shapley Values are often estimated with a small number of stochastic model evaluations. However…
We study the problem of extrapolative controlled generation, i.e., generating sequences with attribute values beyond the range seen in training. This task is of significant importance in automated design, especially drug discovery, where the goal is to design novel proteins that are better (e.g., mo…
Large language models (LLMs) have shown remarkable reasoning capabilities given chain-of-thought prompts (examples with intermediate reasoning steps). Existing benchmarks measure reasoning ability indirectly, by evaluating accuracy on downstream tasks such as mathematical reasoning. However, it is u…
In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We investigate the inductive biases of ICL from the perspective of feature bias: which feature ICL is more likely to use given…
To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations. Under this framework, we identify three common cases where high rewards are inco…
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 prom…
While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work has explored using counterfactually-augmented data (CAD)—data generated by mini…
The term ‘spurious correlations’ has been used in NLP to informally denote any undesirable feature-label correlations. However, a correlation can be undesirable because (i) the feature is irrelevant to the label (e.g. punctuation in a review), or (ii) the feature’s effect on the label depends on the…
Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of intermediate tasks can heavily affect downstream task performanc…
Despite recent progress in abstractive summarization, systems still suffer from faithfulness errors. While prior work has proposed models that improve faithfulness, it is unclear whether the improvement comes from an increased level of extractiveness of the model outputs as one naive way to improve…
Recent work in training large language models (LLMs) to follow natural language instructions has opened up exciting opportunities for natural language interface design. Building on the prior success of large language models in the realm of computer assisted creativity, in this work, we present CoPoe…
Current abstractive summarization systems tend to hallucinate content that is unfaithful to the source document, posing a risk of misinformation. To mitigate hallucination, we must teach the model to distinguish hallucinated summaries from faithful ones. However, the commonly used maximum likelihood…
Machine-in-the-loop writing aims to build models that assist humans to accomplish their writing tasks more effectively. Prior work has found that providing users a machine-written draft or sentence-level continuations has limited success since the generated text tends to deviate from users’ intentio…
The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. Inspired by the recent progress in large language models, we propose in-context tuning (ICT), which recasts task adaptation and prediction as a simple sequence prediction problem: to form the input sequenc…
To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our qu…
Protecting the privacy of user data is crucial for text generation models, which can leak sensitive information during generation. Differentially private (DP) learning methods provide guarantees against identifying the existence of a training sample from model outputs. PATE is a recent DP learning a…
Invariant Risk Minimization (IRM) is a recently proposed framework for out-of-distribution (o.o.d) generalization. Most of the studies on IRM so far have focused on theoretical results, toy problems, and simple models. In this work, we investigate the applicability of IRM to bias mitigation-a speci…
Current approaches to text generation largely rely on autoregressive models and maximum likelihood estimation. This paradigm leads to (i) diverse but low-quality samples due to mismatched learning objective and evaluation metric (likelihood vs. quality) and (ii) exposure bias due to mismatched histo…
Despite agreement on the importance of detecting out-of-distribution (OOD) examples, there is little consensus on the formal definition of the distribution shifts of OOD examples and how to best detect them. We categorize these examples as exhibiting a background shift or semantic shift, and find th…
Learning attacker behavior is an important research topic in security games as security agencies are often uncertain about attackers' decision making. Previous work has focused on developing various behavioral models of attackers based on historical attack data. However, a clever attacker can manipu…
Many machine learning applications involve jointly predicting multiple mutually dependent output variables. Learning to search is a family of methods where the complex decision problem is cast into a sequence of decisions via a search space. Although these methods have shown promise both in theory a…
Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because of strategies’ complex interaction and the non-stationary nature. Most previous work focuses on developing probabilistic models or parame…