arXiv subjects

Masha Fedzechkina

Publications and source records attributed to Masha Fedzechkina.

10 recordsLinked to original sources

arXiv2026

What do your logits know?

Recent work has shown that probing model internals can reveal a wealth of information not apparent from the model generations. This poses a risk of unintentional or malicious information leakage, where model users are able to learn information that the model owner assumed was inaccessible. Using vision-language models as a testbed, we present the first systematic comparison of information retained at different representational levels as it is compressed from the rich information encoded in the residual stream through two natural bottlenecks: low-dimensional projections of the residual stream obtained using tuned lens, and the final top-k logits most likely to impact model's answer. We show that even easily accessible bottlenecks defined by the model's top logit values can leak task-irrelevant information present in an image-based query, in some cases revealing as much information as direct projections of the full residual stream.

cs.AI↗

arXiv2026

Verbalized and Internal Probabilities Are Coupled in Large Language Models

Large language models carry an internal notion of uncertainty in their sampling distribution, i.e., the probabilities they place on generating one answer rather than another. They can also be asked to state a confidence, in words or as a number: a verbalized uncertainty. Prior work suggests that internal probabilities track relative frequencies in the training data, and that verbalized probabilities track explicit probabilistic assertions in the training data. However, we do not know whether these two readouts are aligned, except when frequencies and probabilistic assertions in the training data happen to align. This limits our understanding of when we can use verbalized uncertainties as a proxy for either training data frequencies, or a model's internal distribution. We resolve this gap by systematically exploring how LLMs probability readouts are impacted by training and in-context data, via intervening on the underlying uncertainty sources in the data. We find that both internal and verbalized probability readouts are impacted by both distributional and asserted uncertainty in the training data. Further, we find that verbalized and internal probabilities are aligned beyond what would be expected by independently tracking the same uncertainty sources, suggesting that verbalized probabilities can be used to probe a model's internal distribution.

cs.CL↗

arXiv2026

LLMs are not (consistently) Bayesian: Quantifying internal (in)consistencies of LLMs' probabilistic beliefs

Modern AI systems are being deployed in complex domains such as medicine, science, and law, where it is important that they not only produce correct answers, but also represent and update uncertain beliefs about the world as new evidence arrives. We introduce the novel technique of studying LLMs as information processing rules and utilize the information processing gap to study the internal (in)consistencies of how LLMs update their probabilistic beliefs from evidence. Our extensive experiments evaluate multiple approaches in which LLMs can incorporate evidence into their beliefs. Some of these approaches produce (nearly) Bayesian updates; others seem to use a learned heuristic. Surprisingly, the non-Bayesian heuristic updates often outperform exact Bayesian computation in terms of downstream task performance -- indicating the LLMs' probabilistic models of the world are misspecified. Lastly, we show how our measure can provide diagnostics to identify issues with LLM-powered inferential systems.

cs.LG↗

arXiv2026

DSO: Direct Steering Optimization for Bias Mitigation

Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired individuals. Yet, VLM decisions are influenced by the perceived demographic attributes of people in the input, which can lead to biased outcomes like failing to identify women as doctors. Moreover, when reducing bias leads to performance loss, users may have varying needs for balancing bias mitigation with overall model capabilities, highlighting the demand for methods that enable controllable bias reduction during inference. Activation steering is a popular approach for inference-time controllability that has shown potential in inducing safer behavior in large language models (LLMs). However, we observe that current steering methods struggle to correct biases, where equiprobable outcomes across demographic groups are required. To address this, we propose Direct Steering Optimization (DSO) which uses reinforcement learning to find linear transformations for steering activations, tailored to mitigate bias while maintaining control over model performance. We demonstrate that DSO achieves state-of-the-art trade-off between fairness and capabilities on both VLMs and LLMs, while offering practitioners inference-time control over the trade-off. Overall, our work highlights the benefit of designing steering strategies that are directly optimized to control model behavior, providing more effective bias intervention than methods that rely on pre-defined heuristics for controllability.

cs.LG↗

arXiv2025

Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks

We introduce a set of training-free ABX-style discrimination tasks to evaluate how multilingual language models represent language identity (form) and semantic content (meaning). Inspired from speech processing, these zero-shot tasks measure whether minimal differences in representation can be reliably detected. This offers a flexible and interpretable alternative to probing. Applied to XLM-R (Conneau et al, 2020) across pretraining checkpoints and layers, we find that language discrimination declines over training and becomes concentrated in lower layers, while meaning discrimination strengthens over time and stabilizes in deeper layers. We then explore probing tasks, showing some alignment between our metrics and linguistic learning performance. Our results position ABX tasks as a lightweight framework for analyzing the structure of multilingual representations.

cs.CL↗

arXiv2025

ExpertLens: Activation steering features are highly interpretable

Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amounts of adaptation data. We ask whether the features discovered by activation steering methods are interpretable. We identify neurons responsible for specific concepts (e.g., ``cat'') using the ``finding experts'' method from research on activation steering and show that the ExpertLens, i.e., inspection of these neurons provides insights about model representation. We find that ExpertLens representations are stable across models and datasets and closely align with human representations inferred from behavioral data, matching inter-human alignment levels. ExpertLens significantly outperforms the alignment captured by word/sentence embeddings. By reconstructing human concept organization through ExpertLens, we show that it enables a granular view of LLM concept representation. Our findings suggest that ExpertLens is a flexible and lightweight approach for capturing and analyzing model representations.

cs.CL↗

arXiv2025

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models

Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is computationally expensive, and sizable language data, which often may not be available. A data-efficient alternative to fine-tuning is model interventions -- a method for manipulating model activations to steer generation into the desired direction. We analyze the effect of a popular intervention (finding experts) on the alignment of cross-lingual representations in mLLMs. We identify the neurons to manipulate for a given language and introspect the embedding space of mLLMs pre- and post-manipulation. We show that modifying the mLLM's activations changes its embedding space such that cross-lingual alignment is enhanced. Further, we show that the changes to the embedding space translate into improved downstream performance on retrieval tasks, with up to 2x improvements in top-1 accuracy on cross-lingual retrieval.

cs.CL↗

arXiv2025

Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter

Cross-lingual transfer is a popular approach to increase the amount of training data for NLP tasks in a low-resource context. However, the best strategy to decide which cross-lingual data to include is unclear. Prior research often focuses on a small set of languages from a few language families and/or a single task. It is still an open question how these findings extend to a wider variety of languages and tasks. In this work, we analyze cross-lingual transfer for 263 languages from a wide variety of language families. Moreover, we include three popular NLP tasks: POS tagging, dependency parsing, and topic classification. Our findings indicate that the effect of linguistic similarity on transfer performance depends on a range of factors: the NLP task, the (mono- or multilingual) input representations, and the definition of linguistic similarity.

cs.CL↗

arXiv2022

On the role of Lip Articulation in Visual Speech Perception

Generating realistic lip motion from audio to simulate speech production is critical for driving natural character animation. Previous research has shown that traditional metrics used to optimize and assess models for generating lip motion from speech are not a good indicator of subjective opinion of animation quality. Devising metrics that align with subjective opinion first requires understanding what impacts human perception of quality. In this work, we focus on the degree of articulation and run a series of experiments to study how articulation strength impacts human perception of lip motion accompanying speech. Specifically, we study how increasing under-articulated (dampened) and over-articulated (exaggerated) lip motion affects human perception of quality. We examine the impact of articulation strength on human perception when considering only lip motion, where viewers are presented with talking faces represented by landmarks, and in the context of embodied characters, where viewers are presented with photo-realistic videos. Our results show that viewers prefer over-articulated lip motion consistently more than under-articulated lip motion and that this preference generalizes across different speakers and embodiments.

cs.SD↗

arXiv2022

Naturalistic Head Motion Generation from Speech

Synthesizing natural head motion to accompany speech for an embodied conversational agent is necessary for providing a rich interactive experience. Most prior works assess the quality of generated head motion by comparing them against a single ground-truth using an objective metric. Yet there are many plausible head motion sequences to accompany a speech utterance. In this work, we study the variation in the perceptual quality of head motions sampled from a generative model. We show that, despite providing more diverse head motions, the generative model produces motions with varying degrees of perceptual quality. We finally show that objective metrics commonly used in previous research do not accurately reflect the perceptual quality of generated head motions. These results open an interesting avenue for future work to investigate better objective metrics that correlate with human perception of quality.

eess.AS↗