Pupil dilation tracks the dynamics of mnemonic interference resolution

Abstract

Mnemonic interference refers to the inability to retrieve a goal-relevant memory due to interference from goal-irrelevant memories. Understanding the causes of such interference and how it is overcome has been a central goal in the science of memory for more than a century. Here, we shed new light on this fundamental issue by tracking participants' pupil response when they encode and retrieve memories in the face of competing goal-irrelevant memories. We show that pupil dilation systematically increased in accordance with interference from competing memory traces when participants retrieved previously learned information. Moreover, our results dissociate two main components in the pupillary response signal: an early component, which peaked in a time window where the pupillary waveform on average had its maximum peak, and a late component, which peaked towards the end of the retrieval task. We provide evidence that the early component is specifically modulated by the cognitive effort needed to handle interference from competing memory traces whereas the late component reflects general task engagement. This is the first demonstration that mnemonic interference resolution can be tracked online in the pupil signal and offers novel insight into the underlying dynamics.

Figure 1

Experimental Design, Memory Performance and Pupillary Changes. (a) Participants encoded 3 words from the same semantic category, engaged in a distracter task and were in a retrieval phase to orally recall the 3 words. This procedure was repeated over 4 cycles. Retrieval commenced with an initiation phase and a response phase. The initiation phase was indicated by a “?” in the center of the screen and the response phase was indicated with a speaker symbol in the center of the screen. Participants were not allowed to respond until the response phase was initiated. The distracter task was to orally count backwards in steps of 7 from a randomly generated three-digit number. In the fourth and final word list, proactive interference from previous word lists continued to build up in the PI condition (middle panel), whereas a release from proactive interference was created by changing the semantic category in the RPI condition (right panel). The semantic categories “furniture” and “metals” are here used to illustrate a possible cycle for both PI and RPI conditions, whereas in the actual experiment all categories were used equally often in all conditions across participants. (b) Average retrieval score for word lists 1–3 and for the fourth and final word list when separated into PI and RPI conditions. (c) Average pupil change in mm (compared to baseline) for word lists 1–3 and for the fourth and final word list when separated into PI and RPI conditions. Error bars denote SEM, **p < 0.01, ***p < 0.001.

Figure 2

Temporal dynamics of pupillary changes. (a) Aggregated trial-locked pupil change in mm during retrieval of the fourth and final word list for PI and RPI conditions. The shaded grey area to the left in the figure represents the initiation phase (2 seconds), i.e. before participants were allowed to respond. Shaded areas for both PI and RPI conditions denote SEM. Black lines in the lower half of the figure denote significant time points (P < 0.05) by permutation tests, corrected for multiple comparisons. (b) Principal component analysis (PCA) on the pupil data. Displayed are standardized component loadings for 3 components accounting for 81.3% of the variance: Pre-response Component (11.0%), Early Component (41.2%) and Late Component (29.1%). (c) Component scores (arbitrary units) for the three components. Error bars denote SEM.

Figure 3

Correlations between mnemonic interference indexes and pupillary difference scores. Correlations between participants’ mnemonic interference index (RPI−PI)/RPI and their respective pupillary difference scores (component scores) between RPI and PI conditions (RPI−PI) when retrieving the final (fourth) word lists for both the Early and the Late Component.

Figure 4

Pupillary component scores when splitting trials into Successful and Unsuccessful retrieval. Pupillary component scores for PI and RPI conditions when splitting trials into Successful (all 3 words retrieved) and Unsuccessful retrieval (1 or 0 words retrieved). Error bars denote SEM. In cases where participants did not have any Successful or Unsuccessful performance trials, those participants were excluded, which resulted in the following number of participants: PI-High (n = 27), RPI-High (n = 30), PI-Low (n = 29), RPI-Low (n = 20).